<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (Vaguery)</title>
    <link>https://pinboard.in/u:Vaguery/public/</link>
    <description>recent bookmarks from Vaguery</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://donmoynihan.substack.com/p/what-happens-next?r=slfke&amp;triedRedirect=true"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2211.17095"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2202.08708"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.02179"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1907.02858"/>
	<rdf:li rdf:resource="https://nyaspubs.onlinelibrary.wiley.com/doi/full/10.1111/nyas.14321"/>
	<rdf:li rdf:resource="http://simjs.com/index.html"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1804.02101"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1901.06758"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.07662"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1101.0891"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1801.00548"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1711.01092"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1710.00194"/>
	<rdf:li rdf:resource="http://www.fharrell.com/2017/01/classification-vs-prediction.html"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1603.02597"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1501.03992"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1702.03615v2"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1704.07510"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1607.07086"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1508.05837"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1609.05058"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2016/05/27/055715?rss=1%2522"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1604.08354"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1503.03332"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1505.07414"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1512.03492"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1505.01888"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1411.1528"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1406.7563"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1507.08455"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1505.05921"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1503.01678"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1210.2706"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1406.0140"/>
	<rdf:li rdf:resource="http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2308659"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1505.06472"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1505.05310"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2015/04/24/018507"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1403.6804"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1504.01018"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1404.6823"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1412.3678"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1501.07077"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1403.5356"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1411.3904"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1405.2432"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1409.3379"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1408.6589"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1406.4607"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2014/10/14/002287"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1407.1889"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1312.6562"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1408.3333"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1212.1740"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1407.0952"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1205.4265"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1311.1301"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1311.6536"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1403.7373"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1312.6471"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1312.6826"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1401.8081"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1401.3870"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1307.7306"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1302.7149"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1304.6257"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1310.1553"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1311.1704"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1310.8220"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://donmoynihan.substack.com/p/what-happens-next?r=slfke&amp;triedRedirect=true">
    <title>What Happens Next? - by Don Moynihan - Can We Still Govern?</title>
    <dc:date>2024-11-08T13:25:27+00:00</dc:date>
    <link>https://donmoynihan.substack.com/p/what-happens-next?r=slfke&amp;triedRedirect=true</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[I’ve spent a lot of time over the last four years operating on a couple of assumptions: a) that there was a good chance Trump could return as President and b) that his return would dramatically alter the administrative state. As someone who studies public administration, I figured there was some obligation to communicate those risks. Now that Trump will, in fact, return, I want to summarize what are the most likely outcomes based on my prior writing. Doing so also forces me to make predictions, which is a good practice for being explicit about expectations in the present, and being humble about what I will get wrong when I look back at these predictions at some point in the future. And trust me, I would really like to be wrong by overstating the damage to come.

]]></description>
<dc:subject>anti-institutionalism American-cultural-assumptions politics prediction government</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:9af11c78fd96/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:anti-institutionalism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:American-cultural-assumptions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:politics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:government"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2211.17095">
    <title>[2211.17095] Time-shift selection for reservoir computing using a rank-revealing QR algorithm</title>
    <dc:date>2024-11-01T19:11:51+00:00</dc:date>
    <link>https://arxiv.org/abs/2211.17095</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Reservoir computing, a recurrent neural network paradigm in which only the output layer is trained, has demonstrated remarkable performance on tasks such as prediction and control of nonlinear systems. Recently, it was demonstrated that adding time-shifts to the signals generated by a reservoir can provide large improvements in performance accuracy. In this work, we present a technique to choose the time-shifts by maximizing the rank of the reservoir matrix using a rank-revealing QR algorithm. This technique, which is not task dependent, does not require a model of the system, and therefore is directly applicable to analog hardware reservoir computers. We demonstrate our time-shift selection technique on two types of reservoir computer: one based on an opto-electronic oscillator and the traditional recurrent network with a tanh activation function. We find that our technique provides improved accuracy over random time-shift selection in essentially all cases.
]]></description>
<dc:subject>reservoir-computing nonlinear-dynamics neural-networks prediction time-series to-understand indistinguishable-from-magic</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1e8a540476fb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reservoir-computing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:indistinguishable-from-magic"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2202.08708">
    <title>[2202.08708] Learning stochastic dynamics and predicting emergent behavior using transformers</title>
    <dc:date>2024-03-31T00:38:40+00:00</dc:date>
    <link>https://arxiv.org/abs/2202.08708</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We show that a neural network originally designed for language processing can learn the dynamical rules of a stochastic system by observation of a single dynamical trajectory of the system, and can accurately predict its emergent behavior under conditions not observed during training. We consider a lattice model of active matter undergoing continuous-time Monte Carlo dynamics, simulated at a density at which its steady state comprises small, dispersed clusters. We train a neural network called a transformer on a single trajectory of the model. The transformer, which we show has the capacity to represent dynamical rules that are numerous and nonlocal, learns that the dynamics of this model consists of a small number of processes. Forward-propagated trajectories of the trained transformer, at densities not encountered during training, exhibit motility-induced phase separation and so predict the existence of a nonequilibrium phase transition. Transformers have the flexibility to learn dynamical rules from observation without explicit enumeration of rates or coarse-graining of configuration space, and so the procedure used here can be applied to a wide range of physical systems, including those with large and complex dynamical generators.
]]></description>
<dc:subject>neural-networks transformers lattice-chemistry nonlinear-dynamics prediction o.O</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:32d24577b43d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:transformers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:lattice-chemistry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:o.O"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.02179">
    <title>[2012.02179] Reconstructing cellular automata rules from observations at nonconsecutive times</title>
    <dc:date>2020-12-05T01:11:57+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.02179</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recent experiments by Springer and Kenyon have shown that a deep neural network can be trained to predict the action of t steps of Conway's Game of Life automaton given millions of examples of this action on random initial states. However, training was never completely successful for t>1, and even when successful, a reconstruction of the elementary rule (t=1) from t>1 data is not within the scope of what the neural network can deliver. We describe an alternative network-like method, based on constraint projections, where this is possible. From a single data item this method perfectly reconstructs not just the automaton rule but also the states in the time steps it did not see. For a unique reconstruction, the size of the initial state need only be large enough that it and the t−1 states it evolves into contain all possible automaton input patterns. We demonstrate the method on 1D binary cellular automata that take inputs from n adjacent cells. The unknown rules in our experiments are not restricted to simple rules derived from a few linear functions on the inputs (as in Game of Life), but include all 22n possible rules on n inputs. Our results extend to n=6, for which exhaustive rule-search is not feasible. By relaxing translational symmetry in space and also time, our method is attractive as a platform for the learning of binary data, since the discreteness of the variables does not pose the same challenge it does for gradient-based methods.
]]></description>
<dc:subject>via:cshalizi cellular-automata prediction learning-from-data rather-interesting robustness inference to-write-about consider:representation to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1a035887ab30/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cellular-automata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-from-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:robustness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1907.02858">
    <title>[1907.02858] Improved Bounds for Open Online Dial-a-Ride on the Line</title>
    <dc:date>2020-05-03T11:42:47+00:00</dc:date>
    <link>https://arxiv.org/abs/1907.02858</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We consider the open, non-preemptive online Dial-a-Ride problem on the real line, where transportation requests appear over time and need to be served by a single server. We give a lower bound of 2.0585 on the competitive ratio, which is the first bound that strictly separates online Dial-a-Ride on the line from online TSP on the line in terms of competitive analysis, and is the best currently known lower bound even for general metric spaces. On the other hand, we present an algorithm that improves the best known upper bound from 2.9377 to 2.6662. The analysis of our algorithm is tight.
]]></description>
<dc:subject>operations-research planning prediction game-theory rather-interesting to-simulate toy-problems to-write-about consider:visualization consider:genetic-programming computational-complexity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:68d802ac143e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:planning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:game-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:toy-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://nyaspubs.onlinelibrary.wiley.com/doi/full/10.1111/nyas.14321">
    <title>Evaluating the neurophysiological evidence for predictive processing as a model of perception - Walsh - 2020 - Annals of the New York Academy of Sciences - Wiley Online Library</title>
    <dc:date>2020-05-02T13:05:34+00:00</dc:date>
    <link>https://nyaspubs.onlinelibrary.wiley.com/doi/full/10.1111/nyas.14321</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[For many years, the dominant theoretical framework guiding research into the neural origins of perceptual experience has been provided by hierarchical feedforward models, in which sensory inputs are passed through a series of increasingly complex feature detectors. However, the long‐standing orthodoxy of these accounts has recently been challenged by a radically different set of theories that contend that perception arises from a purely inferential process supported by two distinct classes of neurons: those that transmit predictions about sensory states and those that signal sensory information that deviates from those predictions. Although these predictive processing (PP) models have become increasingly influential in cognitive neuroscience, they are also criticized for lacking the empirical support to justify their status. This limited evidence base partly reflects the considerable methodological challenges that are presented when trying to test the unique predictions of these models. However, a confluence of technological and theoretical advances has prompted a recent surge in human and nonhuman neurophysiological research seeking to fill this empirical gap. Here, we will review this new research and evaluate the degree to which its findings support the key claims of PP.

]]></description>
<dc:subject>cognition prediction psychology experiment rather-interesting to-write-about consider:artificial-intelligence looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:20402e0303da/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cognition"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:psychology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:experiment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:artificial-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://simjs.com/index.html">
    <title>SIM.JS | Discrete Event Simulation in JavaScript</title>
    <dc:date>2020-01-22T00:47:27+00:00</dc:date>
    <link>http://simjs.com/index.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[SIM.JS is a library for modeling discrete time event systems:

The library provides constructs to create Entities which are the active actors in the system and encapsulates the state and logic of components in a system.
The entities contend for resources, which can be Facilities (services that are requested by entities; supports FIFO, LIFO with preemption and Processor Sharing service disciplines), Buffers (resources that can store finite amount of tokens) and Stores (resources that can store JavaScript objects).
The entities communicate by waiting on Events or by sending Messages.
Statistics recording and analysis is provided by Data Series Statistics (collection of discrete, time-independent observations), Time Series Statistics (collection of discrete, time-dependent observations) and Population Statistics (the behavior of population growth and decline).
SIM.JS also provides a random number generation library to generate seeded random variates from various distributions, including uniform, exponential, normal, gamma, pareto and others.
]]></description>
<dc:subject>discrete-event-simulator library javascript to-try simulation engineering-design prediction optimization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e6db3adfa73e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:discrete-event-simulator"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:javascript"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-try"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1804.02101">
    <title>[1804.02101] Modeling Popularity in Asynchronous Social Media Streams with Recurrent Neural Networks</title>
    <dc:date>2019-07-25T11:13:57+00:00</dc:date>
    <link>https://arxiv.org/abs/1804.02101</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Understanding and predicting the popularity of online items is an important open problem in social media analysis. Considerable progress has been made recently in data-driven predictions, and in linking popularity to external promotions. However, the existing methods typically focus on a single source of external influence, whereas for many types of online content such as YouTube videos or news articles, attention is driven by multiple heterogeneous sources simultaneously - e.g. microblogs or traditional media coverage. Here, we propose RNN-MAS, a recurrent neural network for modeling asynchronous streams. It is a sequence generator that connects multiple streams of different granularity via joint inference. We show RNN-MAS not only to outperform the current state-of-the-art Youtube popularity prediction system by 17%, but also to capture complex dynamics, such as seasonal trends of unseen influence. We define two new metrics: promotion score quantifies the gain in popularity from one unit of promotion for a Youtube video; the loudness level captures the effects of a particular user tweeting about the video. We use the loudness level to compare the effects of a video being promoted by a single highly-followed user (in the top 1% most followed users) against being promoted by a group of mid-followed users. We find that results depend on the type of content being promoted: superusers are more successful in promoting Howto and Gaming videos, whereas the cohort of regular users are more influential for Activism videos. This work provides more accurate and explainable popularity predictions, as well as computational tools for content producers and marketers to allocate resources for promotion campaigns.
]]></description>
<dc:subject>social-networks prediction machine-learning marketing cart-before-the-horse to-write-about to-simulate consider:performance-measures consider:false-positives</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e9218582ef1d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:marketing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cart-before-the-horse"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:false-positives"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1901.06758">
    <title>[1901.06758] A deep learning approach to real-time parking occupancy prediction in spatio-temporal networks incorporating multiple spatio-temporal data sources</title>
    <dc:date>2019-06-12T13:53:34+00:00</dc:date>
    <link>https://arxiv.org/abs/1901.06758</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A deep learning model is applied for predicting block-level parking occupancy in real time. The model leverages Graph-Convolutional Neural Networks (GCNN) to extract the spatial relations of traffic flow in large-scale networks, and utilizes Recurrent Neural Networks (RNN) with Long-Short Term Memory (LSTM) to capture the temporal features. In addition, the model is capable of taking multiple heterogeneously structured traffic data sources as input, such as parking meter transactions, traffic speed, and weather conditions. The model performance is evaluated through a case study in Pittsburgh downtown area. The proposed model outperforms other baseline methods including multi-layer LSTM and Lasso with an average testing MAPE of 10.6\% when predicting block-level parking occupancies 30 minutes in advance. The case study also shows that, in generally, the prediction model works better for business areas than for recreational locations. We found that incorporating traffic speed and weather information can significantly improve the prediction performance. Weather data is particularly useful for improving predicting accuracy in recreational areas.
]]></description>
<dc:subject>machine-learning city-planning data-analysis looking-to-see prediction deep-learning to-write-about consider:data-sourcing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:74a9aca209d1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:city-planning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:data-sourcing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1709.07662">
    <title>[1709.07662] Estimating the maximum possible earthquake magnitude using extreme value methodology: the Groningen case</title>
    <dc:date>2019-04-27T11:56:00+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.07662</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The area-characteristic, maximum possible earthquake magnitude TM is required by the earthquake engineering community, disaster management agencies and the insurance industry. The Gutenberg-Richter law predicts that earthquake magnitudes M follow a truncated exponential distribution. In the geophysical literature several estimation procedures were proposed, see for instance Kijko and Singh (Acta Geophys., 2011) and the references therein. Estimation of TM is of course an extreme value problem to which the classical methods for endpoint estimation could be applied. We argue that recent methods on truncated tails at high levels (Beirlant et al., Extremes, 2016; Electron. J. Stat., 2017) constitute a more appropriate setting for this estimation problem. We present upper confidence bounds to quantify uncertainty of the point estimates. We also compare methods from the extreme value and geophysical literature through simulations. Finally, the different methods are applied to the magnitude data for the earthquakes induced by gas extraction in the Groningen province of the Netherlands.
]]></description>
<dc:subject>power-laws geology rather-interesting natural-experiments statistics prediction extreme-values to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f53f76f4e834/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:power-laws"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:geology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-experiments"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:extreme-values"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1101.0891">
    <title>[1101.0891] To Explain or to Predict?</title>
    <dc:date>2019-03-03T13:39:04+00:00</dc:date>
    <link>https://arxiv.org/abs/1101.0891</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Statistical modeling is a powerful tool for developing and testing theories by way of causal explanation, prediction, and description. In many disciplines there is near-exclusive use of statistical modeling for causal explanation and the assumption that models with high explanatory power are inherently of high predictive power. Conflation between explanation and prediction is common, yet the distinction must be understood for progressing scientific knowledge. While this distinction has been recognized in the philosophy of science, the statistical literature lacks a thorough discussion of the many differences that arise in the process of modeling for an explanatory versus a predictive goal. The purpose of this article is to clarify the distinction between explanatory and predictive modeling, to discuss its sources, and to reveal the practical implications of the distinction to each step in the modeling process.
]]></description>
<dc:subject>modeling modeling-is-not-mathematics statistics prediction interpretability interestingness (they-forgot-that-one) philosophy-of-science multiobjective-optimization to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3abf85660a41/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling-is-not-mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interpretability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interestingness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:(they-forgot-that-one)"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1801.00548">
    <title>[1801.00548] A Machine Learning Approach to Adaptive Covariance Localization</title>
    <dc:date>2018-03-10T13:34:53+00:00</dc:date>
    <link>https://arxiv.org/abs/1801.00548</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Data assimilation plays a key role in large-scale atmospheric weather forecasting, where the state of the physical system is estimated from model outputs and observations, and is then used as initial condition to produce accurate future forecasts. The Ensemble Kalman Filter (EnKF) provides a practical implementation of the statistical solution of the data assimilation problem and has gained wide popularity as. This success can be attributed to its simple formulation and ease of implementation. EnKF is a Monte-Carlo algorithm that solves the data assimilation problem by sampling the probability distributions involved in Bayes theorem. Because of this, all flavors of EnKF are fundamentally prone to sampling errors when the ensemble size is small. In typical weather forecasting applications, the model state space has dimension 109−1012, while the ensemble size typically ranges between 30−100 members. Sampling errors manifest themselves as long-range spurious correlations and have been shown to cause filter divergence. To alleviate this effect covariance localization dampens spurious correlations between state variables located at a large distance in the physical space, via an empirical distance-dependent function. The quality of the resulting analysis and forecast is greatly influenced by the choice of the localization function parameters, e.g., the radius of influence. The localization radius is generally tuned empirically to yield desirable results.This work, proposes two adaptive algorithms for covariance localization in the EnKF framework, both based on a machine learning approach. The first algorithm adapts the localization radius in time, while the second algorithm tunes the localization radius in both time and space. Numerical experiments carried out with the Lorenz-96 model, and a quasi-geostrophic model, reveal the potential of the proposed machine learning approaches.
]]></description>
<dc:subject>modeling machine-learning prediction rather-interesting looking-to-see approximation algorithms to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1b0d4f68558d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1711.01092">
    <title>[1711.01092] Cost-Optimal Operation of Energy Storage Units: Impact of Uncertainties and Robust Estimator</title>
    <dc:date>2018-02-24T12:31:07+00:00</dc:date>
    <link>https://arxiv.org/abs/1711.01092</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The rapid expansion of wind and solar energy leads to an increasing volatility in the electricity generation. Previous studies have shown that storage devices provide an opportunity to balance fluctuations in the power grid. An economical operation of these devices is linked to solutions of probabilistic optimization problems, due to the fact that future generation is not deterministic in general. For this reason, reliable forecast methods as well as appropriate robust optimization algorithms take an increasingly important role in future power operation systems. Taking an uncertain availability of electricity into account, we present a method to calculate cost-optimal charging strategies for energy storage units. The proposed method solves subproblems which result from a sliding window approach applied on a linear program by utilizing statistical measures. The prerequisite of this method is a recently developed fast algorithm for storage-related optimization problems. To present the potential of the proposed method, a Power-To-Heat storage system is investigated as an example using today's available forecast data and a robust statistical measure. Second, the novel approach proposed here is compared with a common robust optimization method for stochastic scenario problems. In comparison, the proposed method provides lower acquisition costs, especially for today's available forecasts, and is more robust under perturbations in terms of deteriorating predictions, both based on empirical analyses. Furthermore, the introduced approach is applicable to general cost-optimal operation problems and also real-time optimization concerning uncertain acquisition costs.
]]></description>
<dc:subject>operations-research energy prediction time-series nudge-targets performance-measure to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3055b0ec07c1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:energy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1710.00194">
    <title>[1710.00194] Where computer vision can aid physics: dynamic cloud motion forecasting from satellite images</title>
    <dc:date>2018-02-24T12:28:35+00:00</dc:date>
    <link>https://arxiv.org/abs/1710.00194</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper describes a new algorithm for solar energy forecasting from a sequence of Cloud Optical Depth (COD) images. The algorithm is based on the following simple observation: the dynamics of clouds represented by COD images resembles the motion (transport) of a density in a fluid flow. This suggests that, to forecast the motion of COD images, it is sufficient to forecast the flow. The latter, in turn, can be accomplished by fitting a parametric model of the fluid flow to the COD images observed in the past. Namely, the learning phase of the algorithm is composed of the following steps: (i) given a sequence of COD images, the snapshots of the optical flow are estimated from two consecutive COD images; (ii) these snapshots are then assimilated into a Navier-Stokes Equation (NSE), i.e. an initial velocity field for NSE is selected so that the corresponding NSE' solution is as close as possible to the optical flow snapshots. The prediction phase consists of utilizing a linear transport equation, which describes the propagation of COD images in the fluid flow predicted by NSE, to estimate the future motion of the COD images. The algorithm has been tested on COD images provided by two geostationary operational environmental satellites from NOAA serving the west-hemisphere.
]]></description>
<dc:subject>image-processing prediction nudge-targets consider:looking-to-see representation low-hanging-fruit</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5014b730df49/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:low-hanging-fruit"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.fharrell.com/2017/01/classification-vs-prediction.html">
    <title>Statistical Thinking: Classification vs. Prediction</title>
    <dc:date>2017-11-12T12:47:28+00:00</dc:date>
    <link>http://www.fharrell.com/2017/01/classification-vs-prediction.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A special problem with classifiers illustrates an important issue.  Users of machine classifiers know that a highly imbalanced sample with regard to a binary outcome variable Y results in a strange classifier.  For example, if the sample has 1000 diseased patients and 1,000,000 non-diseased patients, the best classifier may classify everyone as non-diseased; you will be correct 0.999 of the time.  For this reason the odd practice of subsampling the controls is used in an attempt to balance the frequencies and get some variation that will lead to sensible looking classifiers (users of regression models would never exclude good data to get an answer).  Then they have to, in some ill-defined way, construct the classifier to make up for biasing the sample.  It is simply the case that a classifier trained to a 1/1000 prevalence situation will not be applicable to a population with a vastly different prevalence.  The classifier would have to be re-trained on the new sample, and the patterns detected may change greatly.  Logistic regression on the other hand elegantly handles this situation by either (1) having as predictors the variables that made the prevalence so low, or (2) recalibrating the intercept (only) for another dataset with much higher prevalence.  Classifiers' extreme dependence on prevalence may be enough to make some researchers always use probability estimators instead. One could go so far as to say that classifiers should not be used at all when there is little variation in the outcome variable, and that only tendencies should be modeled.
]]></description>
<dc:subject>philosophy-of-engineering classification statistics machine-learning prediction to-write-about engineering-criticism</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:75301920af7d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-criticism"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1603.02597">
    <title>[1603.02597] Prediction of Infinite Words with Automata</title>
    <dc:date>2017-11-05T14:35:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1603.02597</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In the classic problem of sequence prediction, a predictor receives a sequence of values from an emitter and tries to guess the next value before it appears. The predictor masters the emitter if there is a point after which all of the predictor's guesses are correct. In this paper we consider the case in which the predictor is an automaton and the emitted values are drawn from a finite set; i.e., the emitted sequence is an infinite word. We examine the predictive capabilities of finite automata, pushdown automata, stack automata (a generalization of pushdown automata), and multihead finite automata. We relate our predicting automata to purely periodic words, ultimately periodic words, and multilinear words, describing novel prediction algorithms for mastering these sequences.]]></description>
<dc:subject>formal-languages automata consider:looking-to-see prediction modeling to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8442e47e6ed1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:formal-languages"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:automata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1501.03992">
    <title>[1501.03992] PSPACE-Completeness of Majority Automata Networks</title>
    <dc:date>2017-10-15T11:43:13+00:00</dc:date>
    <link>https://arxiv.org/abs/1501.03992</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We study the dynamics of majority automata networks when the vertices are updated according to a block sequential updating scheme. In particular, we show that the complexity of the problem of predicting an eventual state change in some vertex, given an initial configuration, is PSPACE-complete.
]]></description>
<dc:subject>cellular-automata computational-complexity prediction nudge-targets consider:looking-to-see to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5f077633a1c2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cellular-automata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1702.03615v2">
    <title>[1702.03615v2] Online Prediction with Selfish Experts</title>
    <dc:date>2017-09-30T12:46:19+00:00</dc:date>
    <link>https://arxiv.org/abs/1702.03615v2</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We consider the problem of binary prediction with expert advice in settings where experts have agency and seek to maximize their credibility. This paper makes three main contributions. First, it defines a model to reason formally about settings with selfish experts, and demonstrates that "incentive compatible" (IC) algorithms are closely related to the design of proper scoring rules. Designing a good IC algorithm is easy if the designer's loss function is quadratic, but for other loss functions, novel techniques are required. Second, we design IC algorithms with good performance guarantees for the absolute loss function. Third, we give a formal separation between the power of online prediction with selfish experts and online prediction with honest experts by proving lower bounds for both IC and non-IC algorithms. In particular, with selfish experts and the absolute loss function, there is no (randomized) algorithm for online prediction-IC or otherwise-with asymptotically vanishing regret.
]]></description>
<dc:subject>mechanism-design prediction rather-interesting collective-behavior markets game-theory nudge-targets consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5011835b4860/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mechanism-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-behavior"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:markets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:game-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1704.07510">
    <title>[1704.07510] Knotting probability and the scaling behavior of self-avoiding polygons under a topological constraint</title>
    <dc:date>2017-04-26T11:19:04+00:00</dc:date>
    <link>https://arxiv.org/abs/1704.07510</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We define the knotting probability of a knot K by the probability for a random polygon (RP) or self-avoiding polygon (SAP) with N segments having the knot type K. As a model of circular DNA we introduce the SAP consisting of impenetrable cylindrical segments of unit length in which the radius rex of segments corresponds to the screening length of DNA surrounded by counter ions. For various prime and composite knots we numerically show that a compact formula gives good fitted curves to the data of the knotting probabilities for the cylindrical SAP as a function of segment number N and cylindrical radius rex. It connects the small-N to the large-N regions and even to lattice knots for large values of radius rex such as satisfying 2rex=1/4. We suggest that if radius rex is large, the trefoil knot and its composite knots are dominant among the nontrivial knots in SAPs. We then study topological swelling that the mean-square radius of gyration of the cylindrical SAP with fixed knot is much larger than that of under no topological constraint if radius rex is small and N is large enough. We argue that the finite-size effect is significant in it where the characteristic length of the knotting probability gives the topological scale. We show that for any value of radius rex a three-parameter formula gives a good fitted curve to the plot of the mean-square gyration radius of the cylindrical SAP with a given knot K against segment number N. With the curves we evaluate the effective scaling exponent. We suggest that it increases with respect to the upper limit of N and gradually approaches the scaling exponent of self-avoiding walks even in the case of zero thickness as the upper limit of N becomes infinitely large.
]]></description>
<dc:subject>knot-theory inference rather-interesting prediction probability-theory nudge-targets consider:looking-to-see consider:rediscovery consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:02ad6c2e29ad/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:knot-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:rediscovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1607.07086">
    <title>[1607.07086] An Actor-Critic Algorithm for Sequence Prediction</title>
    <dc:date>2017-02-23T22:15:52+00:00</dc:date>
    <link>https://arxiv.org/abs/1607.07086</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL). Current log-likelihood training methods are limited by the discrepancy between their training and testing modes, as models must generate tokens conditioned on their previous guesses rather than the ground-truth tokens. We address this problem by introducing a \textit{critic} network that is trained to predict the value of an output token, given the policy of an \textit{actor} network. This results in a training procedure that is much closer to the test phase, and allows us to directly optimize for a task-specific score such as BLEU. Crucially, since we leverage these techniques in the supervised learning setting rather than the traditional RL setting, we condition the critic network on the ground-truth output. We show that our method leads to improved performance on both a synthetic task, and for German-English machine translation. Our analysis paves the way for such methods to be applied in natural language generation tasks, such as machine translation, caption generation, and dialogue modelling.
]]></description>
<dc:subject>generative-models neural-networks rather-interesting time-series prediction to-write-about to-try nudge-targets consider:deneuralizing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a8a38bc25e99/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-try"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:deneuralizing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1508.05837">
    <title>[1508.05837] Hydroassets Portfolio Management for Intraday Electricity Trading in a Discrete Time Stochastic Optimization Perspective</title>
    <dc:date>2017-01-08T14:32:47+00:00</dc:date>
    <link>https://arxiv.org/abs/1508.05837</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Hydro storage system optimization is becoming one of the most challenging task in Energy Finance. Following the Blomvall and Lindberg (2002) interior point model, we set up a stochastic multiperiod optimization procedure by means of a "bushy" recombining tree that provides fast computational results. Inequality constraints are packed into the objective function by the logarithmic barrier approach and the utility function is approximated by its second order Taylor polynomial. The optimal solution for the original problem is obtained as a diagonal sequence where the first diagonal dimension is the parameter controlling the logarithmic penalty and the second is the parameter for the Newton step in the construction of the approximated solution. Optimal intraday electricity trading and water values for hydroassets as shadow prices are computed. The algorithm is implemented in Mathematica.
]]></description>
<dc:subject>portfolio-theory operations-research financial-engineering time-series prediction models-and-modes nudge-targets consider:performance-measures consider:metaheuristics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6055ba5c2345/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:portfolio-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:financial-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:metaheuristics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1609.05058">
    <title>[1609.05058] A Formal Solution to the Grain of Truth Problem</title>
    <dc:date>2016-10-31T12:53:34+00:00</dc:date>
    <link>https://arxiv.org/abs/1609.05058</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A Bayesian agent acting in a multi-agent environment learns to predict the other agents' policies if its prior assigns positive probability to them (in other words, its prior contains a \emph{grain of truth}). Finding a reasonably large class of policies that contains the Bayes-optimal policies with respect to this class is known as the \emph{grain of truth problem}. Only small classes are known to have a grain of truth and the literature contains several related impossibility results. In this paper we present a formal and general solution to the full grain of truth problem: we construct a class of policies that contains all computable policies as well as Bayes-optimal policies for every lower semicomputable prior over the class. When the environment is unknown, Bayes-optimal agents may fail to act optimally even asymptotically. However, agents based on Thompson sampling converge to play {\epsilon}-Nash equilibria in arbitrary unknown computable multi-agent environments. While these results are purely theoretical, we show that they can be computationally approximated arbitrarily closely.
]]></description>
<dc:subject>artificial-intelligence collective-intelligence collective-behavior prediction agent-based evolutionary-economics nudge-targets consider:representation to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8968781ed86f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-behavior"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:agent-based"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-economics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2016/05/27/055715?rss=1%2522">
    <title>Accurate prediction of single-cell DNA methylation states using deep learning | bioRxiv</title>
    <dc:date>2016-06-06T10:55:29+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2016/05/27/055715?rss=1%2522</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recent technological advances have enabled assaying DNA methylation in single cells. Current protocols are limited by incomplete CpG coverage and hence methods to predict missing methylation states are critical to enable genome-wide analyses. We here report DeepCpG, a computational approach based on deep neural networks to predict DNA methylation states from DNA sequence and incomplete methylation profiles in single cells. We validate DeepCpG on mouse embryonic stem cells, where we report substantially more accurate predictions than previous methods. Additionally, we show that DeepCpG provides new insights for interpreting the sources of epigenetic diversity. Our model can be used to estimate the effect of single nucleotide changes and we uncover sequence motifs that are associated with DNA methylation level and epigenetic heterogeneity.

]]></description>
<dc:subject>bioinformatics deep-learning neural-networks machine-learning prediction nudge-targets consider:rediscovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6d5a8c061369/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:rediscovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1604.08354">
    <title>[1604.08354] Inferring interaction partners from protein sequences</title>
    <dc:date>2016-05-01T12:50:48+00:00</dc:date>
    <link>http://arxiv.org/abs/1604.08354</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Specific protein-protein interactions are crucial in the cell, both to ensure the formation and stability of multi-protein complexes, and to enable signal transduction in various pathways. Functional interactions between proteins result in coevolution between the interaction partners. Hence, the sequences of interacting partners are correlated. Here we exploit these correlations to accurately identify which proteins are specific interaction partners from sequence data alone. Our general approach, which employs a pairwise maximum entropy model to infer direct couplings between residues, has been successfully used to predict the three-dimensional structures of proteins from sequences. Building on this approach, we introduce an iterative algorithm to predict specific interaction partners from among the members of two protein families. We assess the algorithm's performance on histidine kinases and response regulators from bacterial two-component signaling systems. The algorithm proves successful without any a priori knowledge of interaction partners, yielding a striking 0.93 true positive fraction on our complete dataset, and we uncover the origin of this surprising success. Finally, we discuss how our method could be used to predict novel protein-protein interactions.
]]></description>
<dc:subject>bioinformatics machine-learning systems-biology algorithms prediction nudge-targets consider:feature-discovery consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f945fc799b7b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1503.03332">
    <title>[1503.03332] On the long-term correlations and multifractal properties of electric arc furnace time series</title>
    <dc:date>2016-03-26T20:53:25+00:00</dc:date>
    <link>http://arxiv.org/abs/1503.03332</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper, we study long-term correlations and multifractal properties elaborated from time series of three-phase current signals coming from an industrial electric arc furnace plant. Implicit sinusoidal trends are suitably detected by considering the scaling of the fluctuation functions. Time series are then filtered via a Fourier-based analysis, removing hence such strong periodicities. In the filtered time series we detected long-term, positive correlations. The presence of positive correlations is in agreement with the typical V--I characteristic (hysteresis) of the electric arc furnace, providing thus a sound physical justification for the memory effects found in the current time series. The multifractal signature is strong enough in the filtered time series to be effectively classified as multifractal.
]]></description>
<dc:subject>time-series data-analysis prediction industrial-design nudge-targets consider:pareto-GP symbolic-regression</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7bd70675e16f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:industrial-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:pareto-GP"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:symbolic-regression"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1505.07414">
    <title>[1505.07414] Sufficient Forecasting Using Factor Models</title>
    <dc:date>2015-12-30T12:42:29+00:00</dc:date>
    <link>http://arxiv.org/abs/1505.07414</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We consider forecasting a single time series when there is a large number of predictors and a possible nonlinear effect. The dimensionality was first reduced via a high-dimensional (approximate) factor model implemented by the principal component analysis. Using the extracted factors, we develop a novel forecasting method called the sufficient forecasting, which provides a set of sufficient predictive indices, inferred from high-dimensional predictors, to deliver additional predictive power. The projected principal component analysis will be employed to enhance the accuracy of inferred factors when a semi-parametric (approximate) factor model is assumed. Our method is also applicable to cross-sectional sufficient regression using extracted factors. The connection between the sufficient forecasting and the deep learning architecture is explicitly stated. The sufficient forecasting correctly estimates projection indices of the underlying factors even in the presence of a nonparametric forecasting function. The proposed method extends the sufficient dimension reduction to high-dimensional regimes by condensing the cross-sectional information through factor models. We derive asymptotic properties for the estimate of the central subspace spanned by these projection directions as well as the estimates of the sufficient predictive indices. We further show that the natural method of running multiple regression of target on estimated factors yields a linear estimate that actually falls into this central subspace. Our method and theory allow the number of predictors to be larger than the number of observations. We finally demonstrate that the sufficient forecasting improves upon the linear forecasting in both simulation studies and an empirical study of forecasting macroeconomic variables.
]]></description>
<dc:subject>time-series prediction regression feature-construction feature-extraction machine-learning nudge-targets consider:compare-to-Pareto-GP</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:06c7b0e6f5af/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:compare-to-Pareto-GP"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1512.03492">
    <title>[1512.03492] Queue Imbalance as a One-Tick-Ahead Price Predictor in a Limit Order Book</title>
    <dc:date>2015-12-28T14:07:37+00:00</dc:date>
    <link>http://arxiv.org/abs/1512.03492</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We investigate whether the bid/ask queue imbalance in a limit order book (LOB) provides significant predictive power for the direction of the next mid-price movement. We consider this question both in the context of a simple binary classifier, which seeks to predict the direction of the next mid-price movement, and a probabilistic classifier, which seeks to predict the probability that the next mid-price movement will be upwards. To implement these classifiers, we fit logistic regressions between the queue imbalance and the direction of the subsequent mid-price movement for each of 10 liquid stocks on Nasdaq. In each case, we find a strongly statistically significant relationship between these variables. Compared to a simple null model, which assumes that the direction of mid-price changes is uncorrelated with the queue imbalance, we find that our logistic regression fits provide a considerable improvement in binary and probabilistic classification for large-tick stocks, and provide a moderate improvement in binary and probabilistic classification for small-tick stocks. We also perform local logistic regression fits on the same data, and find that this semi-parametric approach slightly outperform our logistic regression fits, at the expense of being more computationally intensive to implement.
]]></description>
<dc:subject>financial-engineering time-series feature-extraction inference prediction nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:58da28e0be5b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:financial-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1505.01888">
    <title>[1505.01888] A Monte Carlo Study of Pairwise Comparisons</title>
    <dc:date>2015-12-14T12:29:02+00:00</dc:date>
    <link>http://arxiv.org/abs/1505.01888</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Consistent approximations obtained by geometric means (GM) and the principal eigenvector (EV), turned out to be close enough for 1,000,000 not-so-inconsistent pairwise comparisons matrices. In this respect both methods are accurate enough for most practical applications. As the enclosed Table 1 demonstrates, the biggest difference between average deviations of GM and EV solutions is 0.00019 for the Euclidean metric and 0.00355 for the Tchebychev metric. 
For practical applications, this precision is far better than expected. After all we are talking, in most cases, about relative subjective comparisons and one tenth of a percent is usually below our threshold of perception.
]]></description>
<dc:subject>knowledge-engineering subjective-modeling prediction wisdom-of-crowds system-of-professions statistics nudge-targets schools-of-thought consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e23c92b2c508/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:knowledge-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:subjective-modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:wisdom-of-crowds"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:system-of-professions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:schools-of-thought"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1411.1528">
    <title>[1411.1528] A network inference method for large-scale unsupervised identification of novel drug-drug interactions</title>
    <dc:date>2015-12-13T11:38:04+00:00</dc:date>
    <link>http://arxiv.org/abs/1411.1528</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Characterizing interactions between drugs is important to avoid potentially harmful combinations, to reduce off-target effects of treatments and to fight antibiotic resistant pathogens, among others. Here we present a network inference algorithm to predict uncharacterized drug-drug interactions. Our algorithm takes, as its only input, sets of previously reported interactions, and does not require any pharmacological or biochemical information about the drugs, their targets or their mechanisms of action. Because the models we use are abstract, our approach can deal with adverse interactions, synergistic/antagonistic/suppressing interactions, or any other type of drug interaction. We show that our method is able to accurately predict interactions, both in exhaustive pairwise interaction data between small sets of drugs, and in large-scale databases. We also demonstrate that our algorithm can be used efficiently to discover interactions of new drugs as part of the drug discovery process.
]]></description>
<dc:subject>pharmaceutical multiobjective-optimization prediction classification interactions nudge-targets engineering-design network-theory inference algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:39cf0733542b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pharmaceutical"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interactions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1406.7563">
    <title>[1406.7563] When is a crowd wise?</title>
    <dc:date>2015-11-01T10:45:35+00:00</dc:date>
    <link>http://arxiv.org/abs/1406.7563</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Numerous studies and anecdotes demonstrate the "wisdom of the crowd," the surprising accuracy of a group's aggregated judgments. Less is known, however, about the generality of crowd wisdom. For example, are crowds wise even if their members have systematic judgmental biases, or can influence each other before members render their judgments? If so, are there situations in which we can expect a crowd to be less accurate than skilled individuals? We provide a precise but general definition of crowd wisdom: A crowd is wise if a linear aggregate, for example a mean, of its members' judgments is closer to the target value than a randomly, but not necessarily uniformly, sampled member of the crowd. Building on this definition, we develop a theoretical framework for examining, a priori, when and to what degree a crowd will be wise. We systematically investigate the boundary conditions for crowd wisdom within this framework and determine conditions under which the accuracy advantage for crowds is maximized. Our results demonstrate that crowd wisdom is highly robust: Even if judgments are biased and correlated, one would need to nearly deterministically select only a highly skilled judge before an individual's judgment could be expected to be more accurate than a simple averaging of the crowd. Our results also provide an accuracy rationale behind the need for diversity of judgments among group members. Contrary to folk explanations of crowd wisdom which hold that judgments should ideally be independent so that errors cancel out, we find that crowd wisdom is maximized when judgments systematically differ as much as possible. We re-analyze data from two published studies that confirm our theoretical results.
]]></description>
<dc:subject>aggregation wisdom-of-crowds prediction probability-theory economics via:cshalizi nudge-targets consider:robustness consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2e04f7d8eddc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:aggregation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:wisdom-of-crowds"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:probability-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:economics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:robustness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1507.08455">
    <title>[1507.08455] Semipredictable dynamical systems</title>
    <dc:date>2015-09-12T20:54:15+00:00</dc:date>
    <link>http://arxiv.org/abs/1507.08455</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A new class of dynamical systems, termed semipredictable dynamical systems, is presented. The spatiotemporal evolution of these systems have both predictable and unpredictable traits, as found in natural complex systems. We show that the dynamics of any deterministic nonlinear cellular automaton with p possible dynamical states can be decomposed at each instant of time in a unique superposition of N cellular automata with p0, p1,... pN−1 dynamical states each, and where the pk∈ℕ, k∈[0,N−1] are the N prime factors of p. These N cellular automata work on different layers of the dynamics of the original cellular automaton and even when the full spatiotemporal evolution can be unpredictable, we show that certain traits can be exactly predicted. We present an explicit example of such a system, consisting on a cellular automaton acting on a neighborhood of two sites and 12 symbols and whose rule table corresponds to the smallest Moufang loop M12(S3,2).
]]></description>
<dc:subject>complex-systems nonlinear-dynamics cellular-automata prediction rather-interesting formalization nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d94342158e41/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:complex-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cellular-automata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:formalization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1505.05921">
    <title>[1505.05921] Identifying Modes of Intent from Driver Behaviors in Dynamic Environments</title>
    <dc:date>2015-09-12T13:23:20+00:00</dc:date>
    <link>http://arxiv.org/abs/1505.05921</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In light of growing attention of intelligent vehicle systems, we propose developing a driver model that uses a hybrid system formulation to capture the intent of the driver. This model hopes to capture human driving behavior in a way that can be utilized by semi- and fully autonomous systems in heterogeneous environments. We consider a discrete set of high level goals or intent modes, that is designed to encompass the decision making process of the human. A driver model is derived using a dataset of lane changes collected in a realistic driving simulator, in which the driver actively labels data to give us insight into her intent. By building the labeled dataset, we are able to utilize classification tools to build the driver model using features of based on her perception of the environment, and achieve high accuracy in identifying driver intent. Multiple algorithms are presented and compared on the dataset, and a comparison of the varying behaviors between drivers is drawn. Using this modeling methodology, we present a model that can be used to assess driver behaviors and to develop human-inspired safety metrics that can be utilized in intelligent vehicular systems.
]]></description>
<dc:subject>autonomous-cars robotics inference feature-extraction prediction nudge-targets consider:rediscovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f1ae6c7a19ec/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:autonomous-cars"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:robotics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:rediscovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1503.01678">
    <title>[1503.01678] Prediction in Projection</title>
    <dc:date>2015-09-10T12:54:42+00:00</dc:date>
    <link>http://arxiv.org/abs/1503.01678</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Prediction models that capture and use the structure of state-space dynamics can be very effective. In practice, however, one rarely has access to full information about that structure, and accurate reconstruction of the dynamics from scalar time-series data---e.g., via delay-coordinate embedding---can be a real challenge. In this paper, we show that forecast models that employ incomplete embeddings of the dynamics can produce surprisingly accurate predictions of the state of a dynamical system. In particular, we demonstrate the effectiveness of a simple near-neighbor forecast technique that works with a two-dimensional embedding. Even though correctness of the topology is not guaranteed for incomplete reconstructions like this, the dynamical structure that they capture allows for accurate predictions---in many cases, even more accurate than predictions generated using a full embedding. This could be very useful in the context of real-time forecasting, where the human effort required to produce a correct delay-coordinate embedding is prohibitive.
]]></description>
<dc:subject>nonlinear-dynamics prediction chaos time-series statistics modeling nudge-targets rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6841a255ca5c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:chaos"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1210.2706">
    <title>[1210.2706] Optimality Gap of Asymptotically-derived Prescriptions with Applications to Queueing Systems</title>
    <dc:date>2015-08-29T11:39:28+00:00</dc:date>
    <link>http://arxiv.org/abs/1210.2706</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In complex systems, it is quite common to resort to approximations when optimizing system performance. These approximations typically involve selecting a particular system parameter and then studying the performance of the system as this parameter grows without bound. In such an asymptotic regime, we prove that if the approximation to the objective function is accurate up to (1), then under some regularity conditions, the prescriptions that are derived from this approximation are o(1)-optimal, i.e., their optimality gap is asymptotically zero. A consequence of this result is that the well-known square-root staffing rules for capacity sizing in M/M/s and M/M/s+M queues to minimize the sum of linear expected steady-state customer waiting costs and linear capacity costs are o(1)-optimal. We also discuss extensions of this result for the case of non-linear customer waiting costs in these systems.
]]></description>
<dc:subject>complex-systems nonlinear-dynamics prediction approximation rather-interesting nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5ebb9be83096/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:complex-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1406.0140">
    <title>[1406.0140] Team Selection For Prediction Tasks</title>
    <dc:date>2015-07-20T12:19:48+00:00</dc:date>
    <link>http://arxiv.org/abs/1406.0140</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Given a random variable O∈ℝ and a set of experts E, we describe a method for finding a subset of experts S⊆E whose aggregated opinion best predicts the outcome of O. Therefore, the problem can be regarded as a team formation for performing a prediction task. We show that in case of aggregating experts' opinions by simple averaging, finding the best team (the team with the lowest total error during past k turns) can be modeled with an integer quadratic programming and we prove its NP-hardness whereas its relaxation is solvable in polynomial time. Finally, we do an experimental comparison between different rounding and greedy heuristics and show that our suggested tabu search works effectively. 
]]></description>
<dc:subject>collective-intelligence algorithms machine-learning prediction performance-measure nudge-targets consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5c1597841048/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2308659">
    <title>Pseudo-Mathematics and Financial Charlatanism: The Effects of Backtest Overfitting on Out-of-Sample Performance by David H. Bailey, Jonathan M. Borwein, Marcos Lopez de Prado, Qiji Jim Zhu :: SSRN</title>
    <dc:date>2015-06-14T15:44:43+00:00</dc:date>
    <link>http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2308659</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We prove that high simulated performance is easily achievable after backtesting a relatively small number of alternative strategy configurations, a practice we denote “backtest overfitting”. The higher the number of configurations tried, the greater is the probability that the backtest is overfit. Because most financial analysts and academics rarely report the number of configurations tried for a given backtest, investors cannot evaluate the degree of overfitting in most investment proposals. 

The implication is that investors can be easily misled into allocating capital to strategies that appear to be mathematically sound and empirically supported by an outstanding backtest. Under memory effects, backtest overfitting leads to negative expected returns out-of-sample, rather than zero performance. This may be one of several reasons why so many quantitative funds appear to fail.

]]></description>
<dc:subject>financial-engineering back-testing statistics models amusing rather-interesting prediction models-and-modes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:dc73868d0f27/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:financial-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:back-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:amusing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1505.06472">
    <title>[1505.06472] Partial Information Framework: Aggregating Estimates from Diverse Information Sources</title>
    <dc:date>2015-06-07T12:43:50+00:00</dc:date>
    <link>http://arxiv.org/abs/1505.06472</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Prediction polling is an increasingly popular form of crowdsourcing in which multiple participants estimate the probability or magnitude of some future event. These estimates are then aggregated into a single forecast. Historically, randomness in scientific estimation has been generally assumed to arise from unmeasured factors which are viewed as measurement noise. However, when combining subjective estimates, heterogeneity stemming from differences in the participants' information is often more important than measurement noise. This paper formalizes information diversity as an alternative source of such heterogeneity and introduces a novel modeling framework that is particularly well-suited for prediction polls. A practical specification of this framework is proposed and applied to the task of aggregating probability and point estimates from two real-world prediction polls. In both cases our model outperforms standard measurement-error-based aggregators, hence providing evidence in favor of information diversity being the more important source of heterogeneity.
]]></description>
<dc:subject>data-fusion collective-intelligence wisdom-of-crowds algorithms statistics prediction rather-interesting nudge-targets consider:robustness</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b424078ddfaa/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-fusion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:wisdom-of-crowds"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:robustness"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1505.05310">
    <title>[1505.05310] A New View of Predictive State Methods for Dynamical System Learning</title>
    <dc:date>2015-06-07T12:39:49+00:00</dc:date>
    <link>http://arxiv.org/abs/1505.05310</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recently there has been substantial interest in predictive state methods for learning dynamical systems: these algorithms are popular since they often offer a good tradeoff between computational speed and statistical efficiency. Despite their desirable properties, though, predictive state methods can sometimes be difficult to use in practice. E.g., in contrast to the rich literature on supervised learning methods, which allows us to choose from an extensive menu of models and algorithms to suit the prior beliefs we have about properties of the function to be learned, predictive state dynamical system learning methods are comparatively inflexible: it is as if we were restricted to use only linear regression instead of being allowed to choose decision trees, nonparametric regression, or the lasso. To address this problem, we propose a new view of predictive state methods in terms of instrumental variable regression. This view allows us to construct a wide variety of dynamical system learners simply by swapping in different supervised learning methods. We demonstrate the effectiveness of our proposed methods by experimenting with non-linear regression to learn a hidden Markov model, showing that the resulting algorithm outperforms the correctness of this algorithm follows directly from our general analysis.
]]></description>
<dc:subject>machine-learning prediction online-learning algorithms statistics models-and-modes to-consider</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:64d92867362e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:online-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-consider"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2015/04/24/018507">
    <title>Predicting genetic interactions from Boolean models of biological networks | bioRxiv</title>
    <dc:date>2015-05-26T11:01:10+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2015/04/24/018507</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Genetic interaction can be defined as a deviation of the phenotypic quantitative effect of a double gene mutation from the effect predicted from single mutations using a simple (e.g., multiplicative or linear additive) statistical model. Experimentally characterized genetic interaction networks in model organisms provide important insights into relationships between different biological functions. We describe a computational methodology allowing to systematically and quantitatively characterize a Boolean mathematical model of a biological network in terms of genetic interactions between all loss of function and gain of function mutations with respect to all model phenotypes or outputs. We use the probabilistic framework defined in MaBoSS software, based on continuous time Markov chains and stochastic simulations. In addition, we suggest several computational tools for studying the distribution of double mutants in the space of model phenotype probabilities. We demonstrate this methodology on three published models for each of which we derive the genetic interaction networks and analyze their properties. We classify the obtained interactions according to their class of epistasis, dependence on the chosen initial conditions and phenotype. The use of this methodology for validating mathematical models from experimental data and designing new experiments is discussed.

]]></description>
<dc:subject>bioinformatics molecular-machinery inference boolean-networks gene-regulatory-networks data-fusion prediction algorithms nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f54447946d81/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:molecular-machinery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:boolean-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gene-regulatory-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-fusion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1403.6804">
    <title>[1403.6804] A simple modification for improving inference of non-linear dynamical systems</title>
    <dc:date>2015-05-25T12:14:19+00:00</dc:date>
    <link>http://arxiv.org/abs/1403.6804</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Particle and ensemble filters are increasingly utilized for inference, optimization, and forecast; however, both filtering methods use discrete distributions to simulate continuous state space, a drawback that can lead to degraded performance for non-linear dynamical systems. Here we propose a simple modification, applicable to both particle and ensemble filters, that compensates for this problem. The method randomly replaces one or more model variables or parameters within a fraction of simulated trajectories at each filtering cycle. This modification, termed space re-probing, expands the state space covered by the filter through the introduction of outlying trajectories. We apply the space re-probing modification to three particle filters and three ensemble filters, and use these modified filters to model and forecast influenza epidemics. For both filter types, the space re-probing improves simulation of influenza epidemic curves and the prediction of influenza outbreak peak timing. Further, as fewer particles are needed for the particle filters, the proposed modification reduces the computational cost of these filters.
]]></description>
<dc:subject>modeling data-analysis prediction statistics nudge-targets simulation data-cleaning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:06ac1fdb8efd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-cleaning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1504.01018">
    <title>[1504.01018] A parameter free similarity index based on clustering ability for link prediction in complex networks</title>
    <dc:date>2015-05-25T12:05:32+00:00</dc:date>
    <link>http://arxiv.org/abs/1504.01018</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Link prediction in complex network based on solely topological information is a challenging problem. In this paper, we propose a novel similarity index, which is efficient and parameter free, based on clustering ability. Here clustering ability is defined as average clustering coefficient of nodes with the same degree. The motivation of our idea is that common-neighbors are able to contribute to the likelihood of forming a link because they own some ability of clustering their neighbors together, and then clustering ability defined here is a measure for this capacity. Experimental numerical simulations on both real-world networks and modeled networks demonstrated the high accuracy and high efficiency of the new similarity index compared with three well-known common-neighbor based similarity indices: CN, AA and RA.
]]></description>
<dc:subject>network-theory models statistics prediction nudge-targets inference</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fdea4a25e918/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1404.6823">
    <title>[1404.6823] Model-free quantification of time-series predictability</title>
    <dc:date>2015-03-16T11:19:44+00:00</dc:date>
    <link>http://arxiv.org/abs/1404.6823</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper provides insight into when, why, and how forecast strategies fail when they are applied to complicated time series. We conjecture that the inherent complexity of real-world time-series data---which results from the dimension, nonlinearity, and non-stationarity of the generating process, as well as from measurement issues like noise, aggregation, and finite data length---is both empirically quantifiable and directly correlated with predictability. In particular, we argue that redundancy is an effective way to measure complexity and predictive structure in an experimental time series and that weighted permutation entropy is an effective way to estimate that redundancy. To validate these conjectures, we study 120 different time-series data sets. For each time series, we construct predictions using a wide variety of forecast models, then compare the accuracy of the predictions with the permutation entropy of that time series. We use the results to develop a model-free heuristic that can help practitioners recognize when a particular prediction method is not well matched to the task at hand: that is, when the time series has more predictive structure than that method can capture and exploit.
]]></description>
<dc:subject>information-theory time-series prediction stress-testing feature-construction rather-interesting horse-races nudge-targets consider:stress-testing performance-space-analysis</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:56f6d48e7fdf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:stress-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:stress-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-space-analysis"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1412.3678">
    <title>[1412.3678] Predicting percolation thresholds in networks</title>
    <dc:date>2015-02-08T15:37:17+00:00</dc:date>
    <link>http://arxiv.org/abs/1412.3678</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We consider different methods, that do not rely on numerical simulations of the percolation process, to approximate percolation thresholds in networks. We perform a systematic analysis on synthetic graphs and a collection of 109 real networks to quantify their effectiveness and reliability as prediction tools. Our study reveals that the inverse of the largest eigenvalue of the non-backtracking matrix of the graph often provides a tight lower bound for true percolation threshold. However, in more than 40% of the cases, this indicator is less predictive than the naive expectation value based solely on the moments of the degree distribution. We find that the performance of all indicators becomes worse as the value of the true percolation threshold grows. Thus, none of them represents a good proxy for robustness of extremely fragile networks.
]]></description>
<dc:subject>percolation network-theory graph-theory algorithms prediction rather-interesting nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3627be898c29/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:percolation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graph-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1501.07077">
    <title>[1501.07077] Hierarchy in Gene Expression is Predictive for Adult Acute Myeloid Leukemia</title>
    <dc:date>2015-02-08T12:08:33+00:00</dc:date>
    <link>http://arxiv.org/abs/1501.07077</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Cancer progresses with a change in the structure of the gene network in normal cells. We define a measure of organizational hierarchy in gene networks of affected cells in adult acute myeloid leukemia (AML) patients. With a retrospective cohort analysis based on the gene expression profiles of 116 acute myeloid leukemia patients, we find that the likelihood of future cancer relapse and the level of clinical risk are directly correlated with the level of organization in the cancer related gene network. We also explore the variation of the level of organization in the gene network with cancer progression. We find that this variation is non-monotonic, which implies the fitness landscape in the evolution of AML cancer cells is nontrivial. We further find that the hierarchy in gene expression at the time of diagnosis may be a useful biomarker in AML prognosis.
]]></description>
<dc:subject>bioinformatics gene-networks network-theory machine-learning systems-biology prediction algorithms nudge-targets feature-extraction cancer</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:35f4d81b66f5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:gene-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cancer"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1403.5356">
    <title>[1403.5356] Predicting 2D Turbulence</title>
    <dc:date>2015-02-06T12:15:21+00:00</dc:date>
    <link>http://arxiv.org/abs/1403.5356</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Prediction is a fundamental objective of science. It is more difficult for chaotic and complex systems like turbulence. Here we use information theory to quantify spatial prediction using experimental data from a turbulent soap film. At high Reynolds number Re where a cascade exists, turbulence is becoming easier to predict as the inertial range broadens. A transition corresponding to the emergence of a cascade at low Re is detected by looking at turbulence through prediction.
]]></description>
<dc:subject>information-theory nonlinear-dynamics prediction statistics machine-learning physics! nudge-targets consider:rediscovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2b030bcdd005/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonlinear-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:physics!"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:rediscovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1411.3904">
    <title>[1411.3904] Autocorrelation type functions for big and dirty data series</title>
    <dc:date>2015-02-02T16:50:41+00:00</dc:date>
    <link>http://arxiv.org/abs/1411.3904</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[One form of big data are signals - time series of consecutive values. In physical experiments, billions of values can now be measured within a second. Signals of heart and brain in intensive care, as well as seismic waves, are measured with 100 up to 1000 Hz over hours, days or even years. A song of 3 minutes on CD comprises 16 million values. 
Music and seismic vibrations basically consist of harmonic oscillations for which classical tools like autocorrelation and spectrogram work well. This note presents similar tools for all kinds of rhythmic processes, with non-linear distortion, artefacts, and outliers. Permutation entropy has been used in physics, medicine, and engineering. Big data allow a detailed analysis of ordinal patterns. As new version of permutation entropy, we define a distance to white noise consisting of four curious components. Applications to a variety of data are discussed.
]]></description>
<dc:subject>data-cleaning feature-extraction dimension-reduction time-series algorithms prediction nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e4edd96ac5d4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-cleaning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1405.2432">
    <title>[1405.2432] Functional Bandits</title>
    <dc:date>2014-12-08T11:30:56+00:00</dc:date>
    <link>http://arxiv.org/abs/1405.2432</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We introduce the functional bandit problem, where the objective is to find an arm that optimises a known functional of the unknown arm-reward distributions. These problems arise in many settings such as maximum entropy methods in natural language processing, and risk-averse decision-making, but current best-arm identification techniques fail in these domains. We propose a new approach, that combines functional estimation and arm elimination, to tackle this problem. This method achieves provably efficient performance guarantees. In addition, we illustrate this method on a number of important functionals in risk management and information theory, and refine our generic theoretical results in those cases.
]]></description>
<dc:subject>armed-bandit-problems information-theory machine-learning prediction risk-management inference nudge-targets game-theory formalization performance-measure multiobjective-optimization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:cc39297407cc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:armed-bandit-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:risk-management"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:game-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:formalization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1409.3379">
    <title>[1409.3379] A variant of the h-index to measure recent performance</title>
    <dc:date>2014-11-14T12:20:58+00:00</dc:date>
    <link>http://arxiv.org/abs/1409.3379</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The predictive power of the h-index has been shown to depend for a long time on citations to rather old publications. This has raised doubts about its usefulness for predicting future scientific achievements. Here I investigate a variant which considers only the recent publications and is therefore more useful in academic hiring processes and for the allocation of research resources. It is simply defined in analogy to the usual h-index, but taking into account only the publications from recent years, and it can easily be determined from the ISI Web of Knowledge.
]]></description>
<dc:subject>citation summary-statistics h-index social-networks models-and-modes academic-culture prediction rather-interesting counterexamples</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6dacbd75bc6a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:citation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:summary-statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:h-index"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-and-modes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:academic-culture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:counterexamples"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1408.6589">
    <title>[1408.6589] Uncertainty Aware Query Execution Time Prediction</title>
    <dc:date>2014-11-08T13:55:42+00:00</dc:date>
    <link>http://arxiv.org/abs/1408.6589</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Predicting query execution time is a fundamental issue underlying many database management tasks. Existing predictors rely on information such as cardinality estimates and system performance constants that are difficult to know exactly. As a result, accurate prediction still remains elusive for many queries. However, existing predictors provide a single, point estimate of the true execution time, but fail to characterize the uncertainty in the prediction. In this paper, we take a first step towards providing uncertainty information along with query execution time predictions. We use the query optimizer's cost model to represent the query execution time as a function of the selectivities of operators in the query plan as well as the constants that describe the cost of CPU and I/O operations in the system. By treating these quantities as random variables rather than constants, we show that with low overhead we can infer the distribution of likely prediction errors. We further show that the estimated prediction errors by our proposed techniques are strongly correlated with the actual prediction errors.
]]></description>
<dc:subject>databases prediction estimation nudge-targets online-learning rather-interesting computational-complexity</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:755d7ba9a016/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:databases"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:online-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1406.4607">
    <title>[1406.4607] Uncovering Randomness and Success in Society</title>
    <dc:date>2014-11-08T12:45:54+00:00</dc:date>
    <link>http://arxiv.org/abs/1406.4607</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[An understanding of how individuals shape and impact the evolution of society is vastly limited due to the unavailability of large-scale reliable datasets that can simultaneously capture information regarding individual movements and social interactions. We believe that the popular Indian film industry, 'Bollywood', can provide a social network apt for such a study. Bollywood provides massive amounts of real, unbiased data that spans more than 100 years, and hence this network has been used as a model for the present paper. The nodes which maintain a moderate degree or widely cooperate with the other nodes of the network tend to be more fit (measured as the success of the node in the industry) in comparison to the other nodes. The analysis carried forth in the current work, using a conjoined framework of complex network theory and random matrix theory, aims to quantify the elements that determine the fitness of an individual node and the factors that contribute to the robustness of a network. The authors of this paper believe that the method of study used in the current paper can be extended to study various other industries and organizations.
]]></description>
<dc:subject>social-networks pragmatism what-good-is-it-really modeling prediction rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5d9db2e1b385/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pragmatism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:what-good-is-it-really"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2014/10/14/002287">
    <title>Predicting growth conditions from internal metabolic fluxes in an in-silico model of E. coli | bioRxiv</title>
    <dc:date>2014-11-05T13:04:26+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2014/10/14/002287</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A widely studied problem in systems biology is to predict bacterial phenotype from growth conditions, using mechanistic models such as flux balance analysis (FBA). However, the inverse prediction of growth conditions from phenotype is rarely considered. Here we develop a computational framework to carry out this inverse prediction on a computational model of bacterial metabolism. We use FBA to calculate bacterial phenotypes from growth conditions in E. coli, and then we assess how accurately we can predict the original growth conditions from the phenotypes. Prediction is carried out via regularized multinomial regression. Our analysis provides several important physiological and statistical insights. First, we show that by analyzing metabolic end products we can consistently predict growth conditions. Second, prediction is reliable even in the presence of small amounts of impurities. Third, flux through a relatively small number of reactions per growth source (~10) is sufficient for accurate prediction. Fourth, combining the predictions from two separate models, one trained only on carbon sources and one only on nitrogen sources, performs better than models trained to perform joint prediction. Finally, that separate predictions perform better than a more sophisticated joint prediction scheme suggests that carbon and nitrogen utilization pathways, despite jointly affecting cellular growth, may be fairly decoupled in terms of their dependence on specific assortments of molecular precursors.

]]></description>
<dc:subject>systems-biology models prediction validation-and-verification rather-interesting theoretical-biology theory-and-practice-sitting-in-a-tree</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4304c7fbfd90/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:systems-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:validation-and-verification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theory-and-practice-sitting-in-a-tree"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1407.1889">
    <title>[1407.1889] The Polyhedron-Hitting Problem</title>
    <dc:date>2014-10-16T12:38:05+00:00</dc:date>
    <link>http://arxiv.org/abs/1407.1889</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We consider polyhedral versions of Kannan and Lipton's Orbit Problem (STOC '80 and JACM '86)---determining whether a target polyhedron V may be reached from a starting point x under repeated applications of a linear transformation A in an ambient vector space Q^m. In the context of program verification, very similar reachability questions were also considered and left open by Lee and Yannakakis in (STOC '92). We present what amounts to a complete characterisation of the decidability landscape for the Polyhedron-Hitting Problem, expressed as a function of the dimension m of the ambient space, together with the dimension of the polyhedral target V: more precisely, for each pair of dimensions, we either establish decidability, or show hardness for longstanding number-theoretic open problems.
]]></description>
<dc:subject>computational-complexity open-questions prediction classification nudge-targets consider:summarization consider:probabilistic-thinking consider:estimation consider:intuition-of-a-sort</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6cd5ff0ecb50/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:open-questions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:summarization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:probabilistic-thinking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:intuition-of-a-sort"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1312.6562">
    <title>[1312.6562] Cell size regulation in microorganisms</title>
    <dc:date>2014-09-28T12:18:44+00:00</dc:date>
    <link>http://arxiv.org/abs/1312.6562</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Various rod-shaped bacteria such as the canonical gram negative Escherichia coli or the well-studied gram positive Bacillus subtilis divide symmetrically after they approximately double their volume. Their size at division is not constant, but is typically distributed over a narrow range. Here, we propose an analytically tractable model for cell size control, and calculate the cell size and inter-division time distributions. We suggest ways of extracting the model parameters from experimental data. Existing data for E. coli supports partial size control, and a particular explanation: a cell attempts to add a constant volume from the time of initiation of DNA replication to the next initiation event. This hypothesis explains how bacteria control their tight size distributions and accounts for the experimentally observed correlations between parents and daughters as well as the exponential dependence of size on growth rate.
]]></description>
<dc:subject>microbiology theoretical-biology cell-biology model prediction physiology philosophy-of-science</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2c9c58235b58/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:microbiology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theoretical-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cell-biology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:model"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:physiology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1408.3333">
    <title>[1408.3333] A ratio-based method for estimating an unknown number of classes</title>
    <dc:date>2014-09-07T10:50:59+00:00</dc:date>
    <link>http://arxiv.org/abs/1408.3333</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We wish to estimate the total number of classes in a population. The classical approach assumes that each class independently contributes a Poisson number of representatives to the sample according to its sampling intensity; these intensities follow a stochastic abundance distribution. In this paper we present what we believe to be the first parametric departure from the mixed Poisson framework. We draw on probability theory that characterizes distributions on the integers by the ratios of their consecutive probabilities. Based on these distributions we construct a nonlinear regression model for the ratios of consecutive frequency counts; this allows us to predict the unobserved count and hence to estimate the total diversity. We find that this approach results in realistic estimates with good fits to data and reasonable standard errors, and it is geometrically intuitive. The method is especially well-suited to the high diversity setting typical of modern microbial datasets derived from next-generation sequencing. We demonstrate its performance in low, medium and high diversity contexts, and via simulation. Finally, we present a dataset for which our method outperforms all competitors.
]]></description>
<dc:subject>statistics estimation prediction classification algorithms sampling</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ef19a46b4021/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:estimation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:sampling"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1212.1740">
    <title>[1212.1740] A Graph Partitioning Approach to Predict Patterns in Lateral Inhibition Systems</title>
    <dc:date>2014-08-22T12:32:16+00:00</dc:date>
    <link>http://arxiv.org/abs/1212.1740</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We analyze pattern formation on a network of cells where each cell inhibits its neighbors through cell-to-cell contact signaling. The network is modeled as an interconnection of identical dynamical subsystems each of which represents the signaling reactions in a cell. We search for steady state patterns by partitioning the graph vertices into disjoint classes, where the cells in the same class have the same final fate. To prove the existence of steady states with this structure, we use results from monotone systems theory. Finally, we analyze the stability of these patterns with a block decomposition based on the graph partition.
]]></description>
<dc:subject>pattern-formation prediction models complex-systems emergent-design nudge-targets rather-interesting discrete-mathematics dynamical-systems</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:882eaa11291b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pattern-formation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:complex-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:emergent-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:discrete-mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dynamical-systems"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1407.0952">
    <title>[1407.0952] Predicting Lifetime of Dynamical Networks Experiencing Persistent Random Attacks</title>
    <dc:date>2014-07-27T12:22:41+00:00</dc:date>
    <link>http://arxiv.org/abs/1407.0952</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Empirical estimation of critical points at which complex systems abruptly flip from one state to another is among the remaining challenges in network science. However, due to the stochastic nature of critical transitions it is widely believed that critical points are difficult to estimate, and it is even more difficult, if not impossible, to predict the time such transitions occur [1-4]. We analyze a class of decaying dynamical networks experiencing persistent attacks in which the magnitude of the attack is quantified by the probability of an internal failure, and there is some chance that an internal failure will be permanent. When the fraction of active neighbors declines to a critical threshold, cascading failures trigger a network breakdown. For this class of network we find both numerically and analytically that the time to the network breakdown, equivalent to the network lifetime, is inversely dependent upon the magnitude of the attack and logarithmically dependent on the threshold. We analyze how permanent attacks affect dynamical network robustness and use the network lifetime as a measure of dynamical network robustness offering new methodological insight into system dynamics.
]]></description>
<dc:subject>complex-systems prediction network-theory robustness experiment simulation nudge-targets interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2b0d15e2fab4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:complex-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:network-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:robustness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:experiment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1205.4265">
    <title>[1205.4265] Quantifying synergistic mutual information</title>
    <dc:date>2014-04-19T07:58:02+00:00</dc:date>
    <link>http://arxiv.org/abs/1205.4265</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Quantifying cooperation or synergy among random variables in predicting a single target random variable is an important problem in many complex systems. We review three prior information-theoretic measures of synergy and introduce a novel synergy measure defined as the difference between the whole and the union of its parts. We apply all four measures against a suite of binary circuits to demonstrate that our measure alone quantifies the intuitive concept of synergy across all examples. We show that for our measure of synergy that independent predictors can have positive redundant information.
]]></description>
<dc:subject>information-theory statistics prediction models synergy learning-from-data nudge</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8eeae2c1c345/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:information-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:synergy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-from-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1311.1301">
    <title>[1311.1301] Prediction of residue-residue contacts from protein families using similarity kernels and least squares regularization</title>
    <dc:date>2014-04-07T12:06:37+00:00</dc:date>
    <link>http://arxiv.org/abs/1311.1301</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[One of the most challenging and long-standing problems in computational biology is the prediction of three-dimensional protein structure from amino acid sequence. A promising approach to infer spatial proximity between residues is the study of evolutionary covariance from multiple sequence alignments, especially in light of recent algorithmic improvements and the fast growing size of sequence databases. 
In this paper, we present a simple, fast and accurate algorithm for the prediction of residue-residue contacts based on regularized least squares. The method incorporates in a very natural manner amino acid similarity in the calculation of covariance, and accounts for low number of observations by a regularization parameter that depends on the effective number of sequences in the alignment. Most importantly, inversion of the sample covariance matrix allows the computation of partial correlations between pairs of residues, thereby removing the effect of spurious transitive correlations. When tested on a set of protein families from PFAM, we found the RLS algorithm to have superior performance compared to PSICOV, a state-of-the-art method for contact prediction.
]]></description>
<dc:subject>protein-folding machine-learning partial-solutions prediction nudge-targets consider:more details</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a5f9740f8e49/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:protein-folding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:partial-solutions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:more"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:details"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1311.6536">
    <title>[1311.6536] Universal Codes from Switching Strategies</title>
    <dc:date>2014-04-04T12:06:54+00:00</dc:date>
    <link>http://arxiv.org/abs/1311.6536</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We discuss algorithms for combining sequential prediction strategies, a task which can be viewed as a natural generalisation of the concept of universal coding. We describe a graphical language based on Hidden Markov Models for defining prediction strategies, and we provide both existing and new models as examples. The models include efficient, parameterless models for switching between the input strategies over time, including a model for the case where switches tend to occur in clusters, and finally a new model for the scenario where the prediction strategies have a known relationship, and where jumps are typically between strongly related ones. This last model is relevant for coding time series data where parameter drift is expected. As theoretical ontributions we introduce an interpolation construction that is useful in the development and analysis of new algorithms, and we establish a new sophisticated lemma for analysing the individual sequence regret of parameterised models.
]]></description>
<dc:subject>prediction time-series algorithms collective-intelligence nudge-targets consider:stress-testing consider:detector-extraction</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c2fb467323fc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:stress-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:detector-extraction"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1403.7373">
    <title>[1403.7373] Difficulty Rating of Sudoku Puzzles: An Overview and Evaluation</title>
    <dc:date>2014-04-03T22:15:41+00:00</dc:date>
    <link>http://arxiv.org/abs/1403.7373</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[How can we predict the difficulty of a Sudoku puzzle? We give an overview of difficulty rating metrics and evaluate them on extensive dataset on human problem solving (more then 1700 Sudoku puzzles, hundreds of solvers). The best results are obtained using a computational model of human solving activity. Using the model we show that there are two sources of the problem difficulty: complexity of individual steps (logic operations) and structure of dependency among steps. We also describe metrics based on analysis of solutions under relaxed constraints -- a novel approach inspired by phase transition phenomenon in the graph coloring problem. In our discussion we focus not just on the performance of individual metrics on the Sudoku puzzle, but also on their generalizability and applicability to other problems.
]]></description>
<dc:subject>sudoku performance-measure problem-solving prediction classification nudge-targets consider:stress-testing consider:performance-space constraint-satisfaction</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:be1cf0397b63/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:sudoku"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:problem-solving"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:stress-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-space"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:constraint-satisfaction"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1312.6471">
    <title>[1312.6471] Wind Energy: Forecasting Challenges for Its Operational Management</title>
    <dc:date>2014-04-03T22:13:35+00:00</dc:date>
    <link>http://arxiv.org/abs/1312.6471</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Renewable energy sources, especially wind energy, are to play a larger role in providing electricity to industrial and domestic consumers. This is already the case today for a number of European countries, closely followed by the US and high growth countries, for example, Brazil, India and China. There exist a number of technological, environmental and political challenges linked to supplementing existing electricity generation capacities with wind energy. Here, mathematicians and statisticians could make a substantial contribution at the interface of meteorology and decision-making, in connection with the generation of forecasts tailored to the various operational decision problems involved. Indeed, while wind energy may be seen as an environmentally friendly source of energy, full benefits from its usage can only be obtained if one is able to accommodate its variability and limited predictability. Based on a short presentation of its physical basics, the importance of considering wind power generation as a stochastic process is motivated. After describing representative operational decision-making problems for both market participants and system operators, it is underlined that forecasts should be issued in a probabilistic framework. Even though, eventually, the forecaster may only communicate single-valued predictions. The existing approaches to wind power forecasting are subsequently described, with focus on single-valued predictions, predictive marginal densities and space-time trajectories. Upcoming challenges related to generating improved and new types of forecasts, as well as their verification and value to forecast users, are finally discussed.
]]></description>
<dc:subject>prediction energy energy-grid public-policy statistics nudge-targets consider:numerous meteorology</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b27926cdbf24/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:energy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:energy-grid"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:public-policy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:numerous"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:meteorology"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1312.6826">
    <title>[1312.6826] 3D Interest Point Detection via Discriminative Learning</title>
    <dc:date>2014-03-17T12:09:11+00:00</dc:date>
    <link>http://arxiv.org/abs/1312.6826</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The task of detecting the interest points in 3D meshes has typically been handled by geometric methods. These methods, while greatly describing human preference, can be ill-equipped for handling the variety and subjectivity in human responses. Different tasks have different requirements for interest point detection; some tasks may necessitate high precision while other tasks may require high recall. Sometimes points with high curvature may be desirable, while in other cases high curvature may be an indication of noise. Geometric methods lack the required flexibility to adapt to such changes. As a consequence, interest point detection seems to be well suited for machine learning methods that can be trained to match the criteria applied on the annotated training data. In this paper, we formulate interest point detection as a supervised binary classification problem using a random forest as our classifier. Among other challenges, we are faced with an imbalanced learning problem due to the substantial difference in the priors between interest and non-interest points. We address this by re-sampling the training set. We validate the accuracy of our method and compare our results to those of five state of the art methods on a new, standard benchmark.
]]></description>
<dc:subject>image-processing 3d attention prediction nudge-targets interesting machine-learning random-forests algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c28a4b08067c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:3d"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:attention"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:random-forests"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1401.8081">
    <title>[1401.8081] Minima Hopping Accelerated Path Search: An Efficient Method for Finding Complex Chemical Reaction Pathways</title>
    <dc:date>2014-03-17T12:04:43+00:00</dc:date>
    <link>http://arxiv.org/abs/1401.8081</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Based on Minima Hopping and its capabilities of exploring potential energy surfaces we have developed Minima Hopping Accelerated Path Search (MHAPS) which is a novel algorithm for efficiently finding the reaction paths of complex chemical reactions by sampling collections of energetically low-lying minima and first order saddle points of potential energy surfaces. For this new reaction path search method we developed a highly reliable approach for computing saddle points which is based on the idea of a bar rolling downwards the potential energy landscape. For Lennard-Jones benchmark systems, Minima Hopping Accelerated Path Search was compared to a known mode-following based approach for sampling collections of minima and first order transition states. Although we used a stabilized mode-following technique that reliably allows to follow distinct directions that are defined by the eigenvectors of the Hessian matrix, we observed that Minima Hopping Accelerated Path Search is far superior in finding lowest-barrier reaction paths. By applying Minima Hopping Accelerated Path Search to 75-atom and 102-atom Lennard Jones systems we found previously unknown reaction paths that connect the two lowest minima of the 75-atom system. Compared to previously known paths, the new paths contain a smaller number of intermediate transition states and the highest energy along the paths is significantly lower in energy. In case of the 102-atom system Minima Hopping Accelerated Path Search found a previously unknown energetically low-lying funnel.
]]></description>
<dc:subject>simulation cheminformatics energy-landscapes prediction models nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2ae70f236cf6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cheminformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:energy-landscapes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1401.3870">
    <title>[1401.3870] Learning to Make Predictions In Partially Observable Environments Without a Generative Model</title>
    <dc:date>2014-03-10T18:11:26+00:00</dc:date>
    <link>http://arxiv.org/abs/1401.3870</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[When faced with the problem of learning a model of a high-dimensional environment, a common approach is to limit the model to make only a restricted set of predictions, thereby simplifying the learning problem. These partial models may be directly useful for making decisions or may be combined together to form a more complete, structured model. However, in partially observable (non-Markov) environments, standard model-learning methods learn generative models, i.e. models that provide a probability distribution over all possible futures (such as POMDPs). It is not straightforward to restrict such models to make only certain predictions, and doing so does not always simplify the learning problem. In this paper we present prediction profile models: non-generative partial models for partially observable systems that make only a given set of predictions, and are therefore far simpler than generative models in some cases. We formalize the problem of learning a prediction profile model as a transformation of the original model-learning problem, and show empirically that one can learn prediction profile models that make a small set of important predictions even in systems that are too complex for standard generative models.
]]></description>
<dc:subject>via:cshalizi prediction modeling statistics nudge-targets representation interesting planning local</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2fd6490ed027/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:cshalizi"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:planning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:local"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1307.7306">
    <title>[1307.7306] Kronecker Sum Decompositions of Space-Time Data</title>
    <dc:date>2014-02-26T21:36:11+00:00</dc:date>
    <link>http://arxiv.org/abs/1307.7306</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper we consider the use of the space vs. time Kronecker product decomposition in the estimation of covariance matrices for spatio-temporal data. This decomposition imposes lower dimensional structure on the estimated covariance matrix, thus reducing the number of samples required for estimation. To allow a smooth tradeoff between the reduction in the number of parameters (to reduce estimation variance) and the accuracy of the covariance approximation (affecting estimation bias), we introduce a diagonally loaded modification of the sum of kronecker products representation [1]. We derive a Cramer-Rao bound (CRB) on the minimum attainable mean squared predictor coefficient estimation error for unbiased estimators of Kronecker structured covariance matrices. We illustrate the accuracy of the diagonally loaded Kronecker sum decomposition by applying it to video data of human activity.
]]></description>
<dc:subject>image-analysis video algorithms prediction nudge-targets consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b64c7bbe5d6a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1302.7149">
    <title>[1302.7149] Uncertainty Quantification in Complex Simulation Models Using Ensemble Copula Coupling</title>
    <dc:date>2014-01-18T14:45:42+00:00</dc:date>
    <link>http://arxiv.org/abs/1302.7149</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Critical decisions frequently rely on high-dimensional output from complex computer simulation models that show intricate cross-variable, spatial and temporal dependence structures, with weather and climate predictions being key examples. There is a strongly increasing recognition of the need for uncertainty quantification in such settings, for which we propose and review a general multi-stage procedure called ensemble copula coupling (ECC), proceeding as follows: 1. Generate a raw ensemble, consisting of multiple runs of the computer model that differ in the inputs or model parameters in suitable ways. 2. Apply statistical postprocessing techniques, such as Bayesian model averaging or nonhomogeneous regression, to correct for systematic errors in the raw ensemble, to obtain calibrated and sharp predictive distributions for each univariate output variable individually. 3. Draw a sample from each postprocessed predictive distribution. 4. Rearrange the sampled values in the rank order structure of the raw ensemble to obtain the ECC postprocessed ensemble. The use of ensembles and statistical postprocessing have become routine in weather forecasting over the past decade. We show that seemingly unrelated, recent advances can be interpreted, fused and consolidated within the framework of ECC, the common thread being the adoption of the empirical copula of the raw ensemble. Depending on the use of Quantiles, Random draws or Transformations at the sampling stage, we distinguish the ECC-Q, ECC-R and ECC-T variants, respectively. We also describe relations to the Schaake shuffle and extant copula-based techniques. In a case study, the ECC approach is applied to predictions of temperature, pressure, precipitation and wind over Germany, based on the 50-member European Centre for Medium-Range Weather Forecasts (ECMWF) ensemble.
]]></description>
<dc:subject>simulation prediction collective-intelligence aggregation algorithms interesting nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1c5eaa345220/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simulation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collective-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:aggregation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1304.6257">
    <title>[1304.6257] An Evolutionary Algorithm Approach to Link Prediction in Dynamic Social Networks</title>
    <dc:date>2013-12-20T11:52:03+00:00</dc:date>
    <link>http://arxiv.org/abs/1304.6257</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Many real world, complex phenomena have underlying structures of evolving networks where nodes and links are added and removed over time. A central scientific challenge is the description and explanation of network dynamics, with a key test being the prediction of short and long term changes. For the problem of short-term link prediction, existing methods attempt to determine neighborhood metrics that correlate with the appearance of a link in the next observation period. Recent work has suggested that the incorporation of topological features and node attributes can improve link prediction. We provide an approach to predicting future links by applying Covariance Matrix Adaptation Evolution Strategy (CMA-ES) to optimize weights which are used in a linear combination of sixteen neighborhood and node similarity indices. We examine a large dynamic social network with over 106 nodes (Twitter reciprocal reply networks), both as a test of our general method and as a problem of scientific interest in itself. Our method exhibits fast convergence and high levels of precision for the top twenty predicted links, and to our knowledge, strongly outperforms all extant methods. Based on our findings, we suggest possible factors which may be driving the evolution of Twitter reciprocal reply networks.
]]></description>
<dc:subject>social-networks evolutionary-algorithms hey-I-know-this-guy prediction interesting nudge-targets consider:expanded-ontology</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:adccbdf66844/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-guy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:expanded-ontology"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1310.1553">
    <title>[1310.1553] A Workflow-Forecast Approach To The Task Scheduling Problem In Distributed Computing Systems</title>
    <dc:date>2013-12-19T13:17:12+00:00</dc:date>
    <link>http://arxiv.org/abs/1310.1553</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The aim of this paper is to provide a description of deep-learning-based scheduling approach for academic-purpose high-performance computing systems. The share of academic-purpose distributed computing systems (DCS) reaches 17.4 percents amongst TOP500 supercomputer sites (15.6 percents in performance scale) that makes them a valuable object of research. The core of this approach is to predict the future workflow of the system depending on the previously submitted tasks using deep learning algorithm. Information on predicted tasks is used by the resource management system (RMS) to perform efficient schedule.
]]></description>
<dc:subject>deep-learning operations-research scheduling algorithms prediction nudge-targets consider:symbolic-regression</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:9f240161d7a6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:operations-research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:scheduling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:symbolic-regression"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1311.1704">
    <title>[1311.1704] Scalable Recommendation with Poisson Factorization</title>
    <dc:date>2013-12-04T21:39:19+00:00</dc:date>
    <link>http://arxiv.org/abs/1311.1704</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We develop a Bayesian Poisson matrix factorization model for forming recommendations from sparse user behavior data. These data are large user/item matrices where each user has provided feedback on only a small subset of items, either explicitly (e.g., through star ratings) or implicitly (e.g., through views or purchases). In contrast to traditional matrix factorization approaches, Poisson factorization implicitly models each user's limited attention to consume items. Moreover, because of the mathematical form of the Poisson likelihood, the model needs only to explicitly consider the observed entries in the matrix, leading to both scalable computation and good predictive performance. We develop a variational inference algorithm for approximate posterior inference that scales up to massive data sets. This is an efficient algorithm that iterates over the observed entries and adjusts an approximate posterior over the user/item representations. We apply our method to large real-world user data containing users rating movies, users listening to songs, and users reading scientific papers. In all these settings, Bayesian Poisson factorization outperforms state-of-the-art matrix factorization methods.
]]></description>
<dc:subject>recommendations data-mining modeling prediction feature-extraction algorithms nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:03dd54eb16f7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:recommendations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1310.8220">
    <title>[1310.8220] Prediction of highly cited papers</title>
    <dc:date>2013-12-04T21:35:08+00:00</dc:date>
    <link>http://arxiv.org/abs/1310.8220</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In an article written five years ago [arXiv:0809.0522], we described a method for predicting which scientific papers will be highly cited in the future, even if they are currently not highly cited. Applying the method to real citation data we made predictions about papers we believed would end up being well cited. Here we revisit those predictions, five years on, to see how well we did. Among the over 2000 papers in our original data set, we examine the fifty that, by the measures of our previous study, were predicted to do best and we find that they have indeed received substantially more citations in the intervening years than other papers, even after controlling for the number of prior citations. On average these top fifty papers have received 23 times as many citations in the last five years as the average paper in the data set as a whole, and 15 times as many as the average paper in a randomly drawn control group that started out with the same number of citations. Applying our prediction technique to current data, we also make new predictions of papers that we believe will be well cited in the next few years.
]]></description>
<dc:subject>hey-I-know-this-guy social-networks citation academic-culture prediction</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1d33a3dd8bd5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-guy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:citation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:academic-culture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>