<?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 (cshalizi)</title>
    <link>https://pinboard.in/u:cshalizi/public/</link>
    <description>recent bookmarks from cshalizi</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://www.jstor.org/stable/1403785?seq=1"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2512.15605"/>
	<rdf:li rdf:resource="https://www.pnas.org/doi/10.1073/pnas.2411731121"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007/s10955-025-03528-4"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2508.21055"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007/BF01295322"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1007/s10955-025-03453-6"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2410.02724"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2203.04395"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2102.01938"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2407.15277"/>
	<rdf:li rdf:resource="https://www.pnas.org/doi/full/10.1073/pnas.180265397"/>
	<rdf:li rdf:resource="https://link.springer.com/book/10.1007/3-540-45804-2"/>
	<rdf:li rdf:resource="https://doi.org/10.1016/0022-2496(66)90020-4"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2111.12603"/>
	<rdf:li rdf:resource="https://www.research-collection.ethz.ch/handle/20.500.11850/354751"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2205.13615"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2203.04163"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2110.04338"/>
	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12615"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2107.14268"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2105.04393"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.09045"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2106.13947"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.00308"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1901.08478"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2106.01645"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2104.05095"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2104.07798"/>
	<rdf:li rdf:resource="https://www.cambridge.org/core/journals/journal-of-applied-probability/article/abs/simple-conditions-for-metastability-of-continuous-markov-chains/6EF80575C90D4DF6288943EAD4883D84"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.06040"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2009.12287"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.07290"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1906.03212"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.06936"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.03801"/>
	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12583?campaign=wolacceptedarticle"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2101.02002"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.12917"/>
	<rdf:li rdf:resource="https://journals.sagepub.com/doi/abs/10.1177/0049124118782541"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.07954"/>
	<rdf:li rdf:resource="https://sociologicalscience.com/articles-v7-20-487/"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1607677244"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.14821"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1703.06447"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2012.02303"/>
	<rdf:li rdf:resource="https://link.springer.com/chapter/10.1007/978-3-030-35902-7_9"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.14994"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.14664"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.10985"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1907.00113"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2011.13780"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2005.06623"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2002.02001"/>
	<rdf:li rdf:resource="https://onlinelibrary.wiley.com/doi/full/10.1002/env.1102?casa_token=ocbU79FU42EAAAAA%3AQDyFS0-w-z1X4iyTEguPeij1WKqyFlab8iL4qHNhaVg8STIrrUbdwgliDave2STG6TP7Ue6-ZfbM6g"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1198/108571105X46543"/>
	<rdf:li rdf:resource="https://link.springer.com/article/10.1023/A:1018553807765"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.bj/1605841254"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1600480925"/>
	<rdf:li rdf:resource="https://projecteuclid.org/euclid.aos/1594972821"/>
	<rdf:li rdf:resource="https://ieeexplore.ieee.org/document/8804216"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1912.00401"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1607.07570"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2005.03750"/>
	<rdf:li rdf:resource="https://www.mdpi.com/1099-4300/11/3/385"/>
	<rdf:li rdf:resource="https://www.sciencedirect.com/science/article/abs/pii/S0031320305000233?via%3Dihub"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/math/0606591"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/0912.4480"/>
	<rdf:li rdf:resource="https://epubs.siam.org/doi/abs/10.1137/1035003?casa_token=VQ1U2GEJoAUAAAAA:RWor_QJUmKSrKfuGUlp9flVZPu5RhXtsXYLZYpEK-O-ah6MH27i3zyXrPqw3xrY-oOaRyOtzAME"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1911.12198"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://www.jstor.org/stable/1403785?seq=1">
    <title>Markov and the Birth of Chain Dependence Theory on JSTOR</title>
    <dc:date>2026-06-01T13:58:12+00:00</dc:date>
    <link>https://www.jstor.org/stable/1403785?seq=1</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>in_NB markov_models history_of_mathematics markov.a.a. ergodic_theory mixing free_will</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b76b51010206/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:history_of_mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov.a.a."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:free_will"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2512.15605">
    <title>[2512.15605] Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction</title>
    <dc:date>2026-01-27T03:26:30+00:00</dc:date>
    <link>https://arxiv.org/abs/2512.15605</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Autoregressive models (ARMs) currently constitute the dominant paradigm for large language models (LLMs). Energy-based models (EBMs) represent another class of models, which have historically been less prevalent in LLM development, yet naturally characterize the optimal policy in post-training alignment. In this paper, we provide a unified view of these two model classes. Taking the chain rule of probability as a starting point, we establish an explicit bijection between ARMs and EBMs in function space, which we show to correspond to a special case of the soft Bellman equation in maximum entropy reinforcement learning. Building upon this bijection, we derive the equivalence between supervised learning of ARMs and EBMs. Furthermore, we analyze the distillation of EBMs into ARMs by providing theoretical error bounds. Our results provide insights into the ability of ARMs to plan ahead, despite being based on the next-token prediction paradigm."


--- ETA after skimming: Pretty sure this is just the usual Gibbs-Markov equivalence, but check carefully later.]]></description>
<dc:subject>to:NB large_language_models_(so_called) gibbs_distributions random_fields markov_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:00b414131396/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_language_models_(so_called)"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:gibbs_distributions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:random_fields"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.pnas.org/doi/10.1073/pnas.2411731121">
    <title>A local–global principle for nonequilibrium steady states | PNAS</title>
    <dc:date>2025-12-18T02:50:13+00:00</dc:date>
    <link>https://www.pnas.org/doi/10.1073/pnas.2411731121</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The global steady state of a system in thermal equilibrium exponentially favors configurations with lesser energy. This principle is a powerful explanation of self-organization because energy is a local property of configurations. For nonequilibrium systems, there is no such property for which an analogous principle holds, hence no common explanation of the diverse forms of self-organization they exhibit. However, a flurry of recent empirical results has shown that a local property of configurations called “rattling” predicts the steady states of some nonequilibrium systems, leading to claims of a far-reaching principle of nonequilibrium self-organization. But for which nonequilibrium systems is rattling accurate, and why? We develop a theory of rattling in terms of Markov processes that gives simple and precise answers to these key questions. Our results show that rattling predicts a broader class of nonequilibrium steady states than has been claimed and for different reasons than have been suggested. Its predictions hold to an extent determined by the relative variance of, and correlation between, the local and global “parts” of a steady state. We show how these quantities characterize the local-global relationships of various random walks on random graphs, spin-glass dynamics, and models of animal collective behavior. Surprisingly, we find that the core idea of rattling is so general as to apply to equilibrium and nonequilibrium systems alike."]]></description>
<dc:subject>to:NB non-equilibrium self-organization statistical_mechanics stochastic_processes markov_models randall.dana to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1730b51f604e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:non-equilibrium"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:self-organization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_mechanics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:randall.dana"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007/s10955-025-03528-4">
    <title>Irreversibility as Divergence from Equilibrium | Journal of Statistical Physics</title>
    <dc:date>2025-11-20T20:42:22+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007/s10955-025-03528-4</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The entropy production is commonly interpreted as measuring the distance from equilibrium. However, this explanation lacks a rigorous description due to the absence of a natural equilibrium measure. The present analysis formalizes this interpretation by expressing the entropy production of a Markov system as a divergence with respect to particular equilibrium dynamics. These equilibrium dynamics correspond to the closest reversible systems in the information-theoretic sense. This result yields novel links between nonequilibrium thermodynamics and information geometry."

]]></description>
<dc:subject>to:NB physics non-equilibrium information_geometry markov_models stochastic_processes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:996c6add6ce2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:non-equilibrium"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2508.21055">
    <title>[2508.21055] Modern aspects of Markov chains: entropy, curvature and the cutoff phenomenon</title>
    <dc:date>2025-09-02T02:49:02+00:00</dc:date>
    <link>https://arxiv.org/abs/2508.21055</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The cutoff phenomenon is an abrupt transition from out of equilibrium to equilibrium undergone by certain Markov processes in the limit where the size of the state space tends to infinity: instead of decaying gradually over time, their distance to equilibrium remains close to its maximal value for a while and suddenly drops to zero as the time parameter reaches a critical threshold. Discovered four decades ago in the context of card shuffling, this surprising phenomenon has since then been observed in a variety of models, from random walks on groups or complex networks to interacting particle systems. It is now believed to be universal among fast-mixing high-dimensional processes. Yet, current proofs are heavily model-dependent, and identifying the general conditions that trigger a cutoff remains one of the biggest challenges in the quantitative analysis of finite Markov chains. The purpose of these lecture notes is to provide a self-contained introduction to this fascinating question, and to describe its recently-uncovered relations with entropy, curvature and concentration."]]></description>
<dc:subject>to:NB to_read markov_models stochastic_processes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4b52c6b91f38/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007/BF01295322">
    <title>Subshifts of finite type and sofic systems | Monatshefte für Mathematik</title>
    <dc:date>2025-08-08T03:11:31+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007/BF01295322</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA[--- Finally read, after literally decades of citing it.  (It is indeed as my teachers and co-authors claimed it to be.)]]></description>
<dc:subject>to:NB have_read sofic_processes symbolic_dynamics dynamical_systems markov_models automata_theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:e99618a1664e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sofic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:symbolic_dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:dynamical_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:automata_theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1007/s10955-025-03453-6">
    <title>A Path Method for Non-exponential Ergodicity of Markov Chains and Its Application for Chemical Reaction Systems | Journal of Statistical Physics</title>
    <dc:date>2025-07-08T15:28:11+00:00</dc:date>
    <link>https://link.springer.com/article/10.1007/s10955-025-03453-6</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper, we present criteria for non-exponential ergodicity of continuous-time Markov chains on a countable state space in total variation norm. These criteria can be verified by examining the ratio of transition rates over certain paths. We applied this path method to explore the non-exponential convergence of microscopic biochemical interacting systems. Using reaction network descriptions, we identified special architectures of biochemical systems for non-exponential ergodicity. In essence, we found that reactions forming a cycle in the reaction network can induce non-exponential ergodicity when they significantly dominate other reactions across infinitely many regions of the state space. Interestingly, the special architectures allowed us to construct many detailed balanced and complex balanced biochemical systems that are non-exponentially ergodic. Some of these models are low-dimensional bimolecular systems with few reactions. Thus this work suggests the possibility of discovering or synthesizing stochastic systems arising in biochemistry that possess either detailed balancing or complex balancing and slowly converge to their stationary distribution."]]></description>
<dc:subject>in_NB markov_models ergodic_theory chemistry</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:47b10b880d00/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:chemistry"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2410.02724">
    <title>[2410.02724] Large Language Models as Markov Chains</title>
    <dc:date>2025-02-03T00:40:20+00:00</dc:date>
    <link>https://arxiv.org/abs/2410.02724</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Large language models (LLMs) have proven to be remarkably efficient, both across a wide range of natural language processing tasks and well beyond them. However, a comprehensive theoretical analysis of the origins of their impressive performance remains elusive. In this paper, we approach this challenging task by drawing an equivalence between generic autoregressive language models with vocabulary of size T and context window of size K and Markov chains defined on a finite state space of size (TK). We derive several surprising findings related to the existence of a stationary distribution of Markov chains that capture the inference power of LLMs, their speed of convergence to it, and the influence of the temperature on the latter. We then prove pre-training and in-context generalization bounds and show how the drawn equivalence allows us to enrich their interpretation. Finally, we illustrate our theoretical guarantees with experiments on several recent LLMs to highlight how they capture the behavior observed in practice."

--- ETA after reading the main paper and half the supplementary materials, and skimming the other half:
1. The proof of the existence of a unique invariant distribution is needlessly complicated.  They assume every context produces every symbol with a minimum probability $c>0$.  Thus every length $T$ context is followed by any other context of length $T$ with a minimum probability of $c^T>0$.  Hence, taking successive length-$T$ blocks of symbols as the states, the chain is plainly aperiodic and recurrent.  Moreover, for any distributions f and g over such states, $d(Qf, Qg) \leq d(f,g)$ because $Qf$ and $Qg$ include at least a minimum amount of smearing out over everything, and now we're off.  (I haven't tried to bound the convergence rate this way but it's plainly do-able if I re-read Fogel, or Latosa and Mackey.)  --- ETA: On thinking about this further, the coupling method is probably a better way.  Consider the chain on $X^2$ where each component independently follows the transition matrix $Q$, until the two coordinates hit the same state at once, and then their trajectories merge.  Let $M$ be the time of merger.  It's a familiar result that d(Q^k f, Q^k g) \leq Pr(M > k).  Now there, in this situation, with $K$ symbol types and a context window of length $T$, there are $K^T$ states where we could merge, the probability of the two block chains hitting the same state after one step, $k=1$, is clearly at least $c^{2T}$, and there are $K^T$ such states, so the probability of merger after one step is at least $(Kc^2)^T$.  So the probability of _not_ merging in one step is at most $1-(Kc^2)^T$, i.e., $Pr(M>1) \leq 1-(K c^2)^T$.  Similarly $Pr(M>2) \leq (1-(K c^2)^T)^2$, since that requires not merging on either the first step _or_ the second, and again the probability of merger at either step is at a minimum $(K c^2)^T$.  (Also, we must have $c \leq 1/K$, since $c$ is the minimum probability of producing any of the $K$ symbol types, hence $K c^2 < 1$.)
2. I don't understand how to interpret their in-context theorems at all.]]></description>
<dc:subject>markov_models large_language_models_(so_called) in_NB have_read re:large_language_models_in_statistical_perspective</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:391fa8dedf0b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_language_models_(so_called)"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:large_language_models_in_statistical_perspective"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2203.04395">
    <title>[2203.04395] Equivalences of Geometric Ergodicity of Markov Chains</title>
    <dc:date>2024-12-11T16:02:48+00:00</dc:date>
    <link>https://arxiv.org/abs/2203.04395</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper gathers together different conditions which are all equivalent to geometric ergodicity of time-homogeneous Markov chains on general state spaces. A total of 34 different conditions are presented (27 for general chains plus 7 just for reversible chains), some old and some new, in terms of such notions as convergence bounds, drift conditions, spectral properties, etc., with different assumptions about the distance metric used, finiteness of function moments, initial distribution, uniformity of bounds, and more. Proofs of the connections between the different conditions are provided, mostly self-contained but using some results from the literature where appropriate."]]></description>
<dc:subject>to:NB markov_models mixing ergodic_theory re:almost_none</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bb278df058e6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ergodic_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:almost_none"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2102.01938">
    <title>[2102.01938] How good is Good-Turing for Markov samples?</title>
    <dc:date>2024-08-26T13:47:31+00:00</dc:date>
    <link>https://arxiv.org/abs/2102.01938</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The Good-Turing (GT) estimator for the missing mass (i.e., total probability of missing symbols) in n samples is the number of symbols that appeared exactly once divided by n. For i.i.d. samples, the bias and squared-error risk of the GT estimator can be shown to fall as 1/n by bounding the expected error uniformly over all symbols. In this work, we study convergence of the GT estimator for missing stationary mass (i.e., total stationary probability of missing symbols) of Markov samples on an alphabet  with stationary distribution [πx:x∈] and transition probability matrix (t.p.m.) P. This is an important and interesting problem because GT is widely used in applications with temporal dependencies such as language models assigning probabilities to word sequences, which are modelled as Markov. We show that convergence of GT depends on convergence of (P∼x)n, where P∼x is P with the x-th column zeroed out. This, in turn, depends on the Perron eigenvalue λ∼x of P∼x and its relationship with πx uniformly over x. For randomly generated this http URL and this http URL derived from New York Times and Charles Dickens corpora, we numerically exhibit such uniform-over-x relationships between λ∼x and πx. This supports the observed success of GT in language models and practical text data scenarios. For Markov chains with rank-2, diagonalizable this http URL having spectral gap β, we show minimax rate upper and lower bounds of 1/(nβ5) and 1/(nβ), respectively, for the estimation of stationary missing mass. This theoretical result extends the 1/n minimax rate for i.i.d. or rank-1 this http URL to rank-2 Markov, and is a first such minimax rate result for missing mass of Markov samples."]]></description>
<dc:subject>in_NB probability markov_models good-turing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:990dff2666bf/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:good-turing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2407.15277">
    <title>[2407.15277] Conformal Predictions under Markovian Data</title>
    <dc:date>2024-08-21T17:39:24+00:00</dc:date>
    <link>https://arxiv.org/abs/2407.15277</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study the split Conformal Prediction method when applied to Markovian data. We quantify the gap in terms of coverage induced by the correlations in the data (compared to exchangeable data). This gap strongly depends on the mixing properties of the underlying Markov chain, and we prove that it typically scales as tmixln(n)/n‾‾‾‾‾‾‾‾‾‾√ (where tmix is the mixing time of the chain). We also derive upper bounds on the impact of the correlations on the size of the prediction set. Finally we present K-split CP, a method that consists in thinning the calibration dataset and that adapts to the mixing properties of the chain. Its coverage gap is reduced to tmix/(nln(n)) without really affecting the size of the prediction set. We finally test our algorithms on synthetic and real-world datasets."]]></description>
<dc:subject>conformal_prediction markov_models in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:045f1fa57489/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:conformal_prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.pnas.org/doi/full/10.1073/pnas.180265397">
    <title>Building a dictionary for genomes: Identification of presumptive regulatory sites by statistical analysis (Bussemaker, Li and Siggia, 2000)</title>
    <dc:date>2023-07-25T14:19:26+00:00</dc:date>
    <link>https://www.pnas.org/doi/full/10.1073/pnas.180265397</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The availability of complete genome sequences and mRNA expression data for all genes creates new opportunities and challenges for identifying DNA sequence motifs that control gene expression. An algorithm, “MobyDick,” is presented that decomposes a set of DNA sequences into the most probable dictionary of motifs or words. This method is applicable to any set of DNA sequences: for example, all upstream regions in a genome or all genes expressed under certain conditions. Identification of words is based on a probabilistic segmentation model in which the significance of longer words is deduced from the frequency of shorter ones of various lengths, eliminating the need for a separate set of reference data to define probabilities. We have built a dictionary with 1,200 words for the 6,000 upstream regulatory regions in the yeast genome; the 500 most significant words (some with as few as 10 copies in all of the upstream regions) match 114 of 443 experimentally determined sites (a significance level of 18 standard deviations). When analyzing all of the genes up-regulated during sporulation as a group, we find many motifs in addition to the few previously identified by analyzing the subclusters individually to the expression subclusters. Applying MobyDick to the genes derepressed when the general repressor Tup1 is deleted, we find known as well as putative binding sites for its regulatory partners."

--- This was part of the prehistory/ancestry for CSSR, back in 2000.]]></description>
<dc:subject>to:NB have_read bioinformatics markov_models re:CSSR cleaning_out_the_filing_cabinet_for_the_first_time_since_2005</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9f1cb062df07/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bioinformatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:CSSR"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cleaning_out_the_filing_cabinet_for_the_first_time_since_2005"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/book/10.1007/3-540-45804-2">
    <title>Interactive Markov Chains: The Quest for Quantified Quality | SpringerLink</title>
    <dc:date>2023-05-01T19:57:57+00:00</dc:date>
    <link>https://link.springer.com/book/10.1007/3-540-45804-2</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Markov Chains are widely used as stochastic models to study a broad spectrum of system performance and dependability characteristics. This monograph is devoted to compositional specification and analysis of Markov chains.
"Based on principles known from process algebra, the author systematically develops an algebra of interactive Markov chains. By presenting a number of distinguishing results, of both theoretical and practical nature, the author substantiates the claim that interactive Markov chains are more than just another formalism: Among other, an algebraic theory of interactive Markov chains is developed, devise algorithms to mechanize compositional aggregation are presented, and state spaces of several million states resulting from the study of an ordinary telefone system are analyzed."]]></description>
<dc:subject>in_NB markov_models interacting_particle_systems distributed_systems to_read cleaning_out_the_filing_cabinet_for_the_first_time_since_2005</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:8164ee44d88f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:interacting_particle_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:distributed_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cleaning_out_the_filing_cabinet_for_the_first_time_since_2005"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://doi.org/10.1016/0022-2496(66)90020-4">
    <title>The structure of responses to a sequence of binary events - ScienceDirect</title>
    <dc:date>2023-04-24T21:43:30+00:00</dc:date>
    <link>https://doi.org/10.1016/0022-2496(66)90020-4</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A procedure developed by Foulkes for determining the structure of a sequence of binary events was found to be a useful base-line model of structure determination by human subjects. The structure is represented in terms of the subsequences of events (states) which lead to different probabilities of the events. While the subjects' behavior after each state is not given by the Foulkes procedure, their behavior appeared to be largely a function of the probabilities of the events after each state (matching) and the lastest event in the state (positive recency)."

--- The Foulkes (1959) paper lying behind this is truly wild as a flash of genius but doesn't seem to be online anywhere.  (I may rectify this.)]]></description>
<dc:subject>have_read markov_models cognitive_science variable-length_markov_models_aka_context_trees statistical_inference_for_stochastic_processes re:AoS_project cleaning_out_the_filing_cabinet_for_the_first_time_since_2005 re:dissertation prediction in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:851a2a33fb27/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cognitive_science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:variable-length_markov_models_aka_context_trees"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:cleaning_out_the_filing_cabinet_for_the_first_time_since_2005"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:dissertation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2111.12603">
    <title>[2111.12603] Strong Invariance Principles for Ergodic Markov Processes</title>
    <dc:date>2022-06-19T17:05:18+00:00</dc:date>
    <link>https://arxiv.org/abs/2111.12603</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Strong invariance principles describe the error term of a Brownian approximation of the partial sums of a stochastic process. While these strong approximation results have many applications, the results for continuous-time settings have been limited. In this paper, we obtain strong invariance principles for a broad class of ergodic Markov processes. Strong invariance principles provide a unified framework for analysing commonly used estimators of the asymptotic variance in settings with a dependence structure. We demonstrate how this can be used to analyse the batch means method for simulation output of Piecewise Deterministic Monte Carlo samplers. We also derive a fluctuation result for additive functionals of ergodic diffusions using our strong approximation results."]]></description>
<dc:subject>central_limit_theorem stochastic_processes convergence_of_stochastic_processes markov_models re:almost_none in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:23ae04823e1b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:central_limit_theorem"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:convergence_of_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:almost_none"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.research-collection.ethz.ch/handle/20.500.11850/354751">
    <title>Dynamic Coarse-Graining via Large-Deviation Theory - Research Collection</title>
    <dc:date>2022-06-12T06:11:55+00:00</dc:date>
    <link>https://www.research-collection.ethz.ch/handle/20.500.11850/354751</link>
    <dc:creator>cshalizi</dc:creator><dc:subject>statistical_mechanics non-equilibrium large_deviations stochastic_processes markov_models have_skimmed in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:47e2725ff00f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_mechanics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:non-equilibrium"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_deviations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_skimmed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2205.13615">
    <title>[2205.13615] Limit distributions of branching Markov chains</title>
    <dc:date>2022-06-10T14:07:30+00:00</dc:date>
    <link>https://arxiv.org/abs/2205.13615</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study branching Markov chains on a countable state space (space of types) 𝒳, with the focus on the qualitative aspects of the limit behaviour of the evolving empirical population distributions. No conditions are imposed on the multitype offspring distributions at the points of 𝒳 other than to have the same average and to satisfy a uniform LlogL moment condition. We show that the arising population martingale is uniformly integrable. Convergence of population averages of the branching chain is then put in connection with stationary spaces of the associated ordinary Markov chain on 𝒳 (assumed to be irreducible and transient). This is applied, in particular, to the boundaries of appropriate compactifications of 𝒳. Final considerations consider the general interplay between the measure theoretic boundaries of the branching chain and the associated ordinary chain."

--- Assuming equal-expectation offspring distributions seems a little un-interesting but I should look.]]></description>
<dc:subject>branching_processes markov_models stochastic_processes in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0d1c60549638/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:branching_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2203.04163">
    <title>[2203.04163] Localization Schemes: A Framework for Proving Mixing Bounds for Markov Chains</title>
    <dc:date>2022-06-09T08:19:32+00:00</dc:date>
    <link>https://arxiv.org/abs/2203.04163</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Two recent and seemingly-unrelated techniques for proving mixing bounds for Markov chains are: (i) the framework of Spectral Independence, introduced by Anari, Liu and Oveis Gharan, and its numerous extensions, which have given rise to several breakthroughs in the analysis of mixing times of discrete Markov chains and (ii) the Stochastic Localization technique which has proven useful in establishing mixing and expansion bounds for both log-concave measures and for measures on the discrete hypercube. In this paper, we introduce a framework which connects ideas from both techniques. Our framework unifies, simplifies and extends those two techniques. In its center is the concept of a localization scheme which, to every probability measure, assigns a martingale of probability measures which localize in space as time evolves. As it turns out, to every such scheme corresponds a Markov chain, and many chains of interest appear naturally in this framework. This viewpoint provides tools for deriving mixing bounds for the dynamics through the analysis of the corresponding localization process. Generalizations of concepts of Spectral Independence and Entropic Independence naturally arise from our definitions, and in particular we recover the main theorems in the spectral and entropic independence frameworks via simple martingale arguments (completely bypassing the need to use the theory of high-dimensional expanders). We demonstrate the strength of our proposed machinery by giving short and (arguably) simpler proofs to many mixing bounds in the recent literature, including giving the first O(nlogn) bound for the mixing time of Glauber dynamics on the hardcore-model (of arbitrary degree) in the tree-uniqueness regime."]]></description>
<dc:subject>to:NB stochastic_processes mixing markov_models martingales</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:03c6185cd447/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:martingales"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2110.04338">
    <title>[2110.04338] Learning from non-irreducible Markov chains</title>
    <dc:date>2021-10-18T13:52:08+00:00</dc:date>
    <link>https://arxiv.org/abs/2110.04338</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Most of the existing literature on supervised learning problems focuses on the case when the training data set is drawn from an i.i.d. sample. However, many practical supervised learning problems are characterized by temporal dependence and strong correlation between the marginals of the data-generating process, suggesting that the i.i.d. assumption is not always justified. This problem has been already considered in the context of Markov chains satisfying the Doeblin condition. This condition, among other things, implies that the chain is not singular in its behavior, i.e. it is irreducible. In this article, we focus on the case when the training data set is drawn from a not necessarily irreducible Markov chain. Under the assumption that the chain is uniformly ergodic with respect to the L1-Wasserstein distance, and certain regularity assumptions on the hypothesis class and the state space of the chain, we first obtain a uniform convergence result for the corresponding sample error, and then we conclude learnability of the approximate sample error minimization algorithm and find its generalization bounds. At the end, a relative uniform convergence result for the sample error is also discussed."]]></description>
<dc:subject>to:NB markov_models stochastic_processes learning_theory learning_under_dependence</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:784109e439d5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:learning_under_dependence"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12615">
    <title>Variable Length Markov Chain with Exogenous Covariates - Zambom - - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2021-08-16T03:26:10+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12615</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Markov Chains with variable length are useful stochastic models for data compression that avoid the curse of dimensionality faced by full Markov Chains. In this paper we introduce a Variable Length Markov Chain whose transition probabilities depend not only on the state history but also on exogenous covariates through a generalized linear model. The goal of the proposed procedure is to estimate not only the context of the process, that is, the history of the process that is relevant for predicting the next state, but also the coefficients corresponding to the significant exogenous variables. The proposed method is consistent in the sense that the probability that the estimated context and the coefficients are equal to the true data generating mechanism tends to 1 as the sample size increases. Simulations suggest that, when covariates do contribute to the transition probabilities, the proposed procedure can recover both the tree structure and the regression parameters. It outperforms variable length Markov Chains when covariates are present while yielding comparable results when covariates are absent. For models with fixed length, the accuracy of the proposed algorithm in recovering the true data generating mechanism is close to the methods available in the literature. The proposed methodology is used to predict the gains and losses of the Hang Seng Index based on its own history and three large stock market indices."]]></description>
<dc:subject>to:NB time_series markov_models re:AoS_project statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:dd1ba3024572/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2107.14268">
    <title>[2107.14268] Virtual Markov chains</title>
    <dc:date>2021-08-03T04:43:45+00:00</dc:date>
    <link>https://arxiv.org/abs/2107.14268</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We introduce the space of virtual Markov chains (VMCs) as a projective limit of the spaces of all finite state space Markov chains (MCs), in the same way that the space of virtual permutations is the projective limit of the spaces of all permutations of finite sets. We introduce the notions of virtual initial distribution (VID) and a virtual transition matrix (VTM), and we show that the law of any VMC is uniquely characterized by a pair of a VID and VTM which have to satisfy a certain compatibility condition. Lastly, we study various properties of compact convex sets associated to the theory of VMCs, including that the Birkhoff-von Neumann theorem fails in the virtual setting."]]></description>
<dc:subject>to:NB stochastic_processes markov_models statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:310141c80200/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2105.04393">
    <title>[2105.04393] Breakdown of random matrix universality in Markov models</title>
    <dc:date>2021-07-27T12:07:24+00:00</dc:date>
    <link>https://arxiv.org/abs/2105.04393</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Biological systems need to react to stimuli over a broad spectrum of timescales. If and how this ability can emerge without external fine-tuning is a puzzle. We consider here this problem in discrete Markovian systems, where we can leverage results from random matrix theory. Indeed, generic large transition matrices are governed by universal results, which predict the absence of long timescales unless fine-tuned. We consider an ensemble of transition matrices and motivate a temperature-like variable that controls the dynamic range of matrix elements, which we show plays a crucial role in the applicability of the large matrix limit: as the dynamic range increases, a phase transition occurs whereby the random matrix theory result is avoided, and long relaxation times ensue, in the entire `ordered' phase. We furthermore show that this phase transition is accompanied by a drop in the entropy rate and a peak in complexity, as measured by predictive information (Bialek, Nemenman, Tishby Neural Computation 13(21) 2001). Extending the Markov model to a Hidden Markov model (HMM), we show that observable sequences inherit properties of the hidden sequences, allowing HMMs to be understood in terms of more accessible Markov models. We then apply our findings to fMRI data from 820 human subjects scanned at wakeful rest. We show that the data can be quantitatively understood in terms of the random model, and that brain activity lies close to the phase transition when engaged in unconstrained, task-free cognition -- supporting the brain criticality hypothesis in this context."

--- The last tag is for the "application", everything before that in the abstract seems sensible and interesting.]]></description>
<dc:subject>markov_models random_matrices color_me_skeptical in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:60c9dcd3891e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:random_matrices"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:color_me_skeptical"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2101.09045">
    <title>[2101.09045] Inference of Markov models from trajectories via Large Deviations at Level 2.5 with applications to random walks in disordered media</title>
    <dc:date>2021-07-01T13:29:55+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.09045</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The inference of Markov models from data on stochastic dynamical trajectories over the large time-window T is revisited via the Large Deviations at Level 2.5 for the time-empirical density and the time-empirical flows. The goal is to obtain the large deviations properties for the probability distribution of the inferred Markov parameters in order to characterize their possible fluctuations around the true Markov parameters for large T. The explicit rate functions are given for several settings, namely discrete-time Markov chains, continuous-time Markov jump processes, and diffusion processes in dimension d. Applications to various models of random walks in disordered media are described, where the goal is to infer the quenched disordered variables defining a given disordered sample."]]></description>
<dc:subject>to:NB markov_models large_deviations statistical_inference_for_stochastic_processes statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f99b5b88b07a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_deviations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2106.13947">
    <title>[2106.13947] Optimal prediction of Markov chains with and without spectral gap</title>
    <dc:date>2021-06-30T02:57:36+00:00</dc:date>
    <link>https://arxiv.org/abs/2106.13947</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study the following learning problem with dependent data: Observing a trajectory of length n from a stationary Markov chain with k states, the goal is to predict the next state. For 3≤k≤O(n‾√), using techniques from universal compression, the optimal prediction risk in Kullback-Leibler divergence is shown to be Θ(k2nlognk2), in contrast to the optimal rate of Θ(loglognn) for k=2 previously shown in Falahatgar et al., 2016. These rates, slower than the parametric rate of O(k2n), can be attributed to the memory in the data, as the spectral gap of the Markov chain can be arbitrarily small. To quantify the memory effect, we study irreducible reversible chains with a prescribed spectral gap. In addition to characterizing the optimal prediction risk for two states, we show that, as long as the spectral gap is not excessively small, the prediction risk in the Markov model is O(k2n), which coincides with that of an iid model with the same number of parameters."]]></description>
<dc:subject>to:NB prediction time_series mixing markov_models statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:be4dfa48c5ee/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.00308">
    <title>[2011.00308] Mixing it up: A general framework for Markovian statistics</title>
    <dc:date>2021-06-25T14:55:04+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.00308</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Up to now, the nonparametric analysis of multidimensional continuous-time Markov processes has focussed strongly on specific model choices, mostly related to symmetry of the semigroup. While this approach allows to study the performance of estimators for the characteristics of the process in the minimax sense, it restricts the applicability of results to a rather constrained set of stochastic processes and in particular hardly allows incorporating jump structures. As a consequence, for many models of applied and theoretical interest, no statement can be made about the robustness of typical statistical procedures beyond the beautiful, but limited framework available in the literature. To close this gap, we identify β-mixing of the process and heat kernel bounds on the transition density as a suitable combination to obtain sup-norm and L2 kernel invariant density estimation rates matching the case of reversible multidimenisonal diffusion processes and outperforming density estimation based on discrete i.i.d. or weakly dependent data. Moreover, we demonstrate how up to log-terms, optimal sup-norm adaptive invariant density estimation can be achieved within our general framework based on tight uniform moment bounds and deviation inequalities for empirical processes associated to additive functionals of Markov processes. The underlying assumptions are verifiable with classical tools from stability theory of continuous time Markov processes and PDE techniques, which opens the door to evaluate statistical performance for a vast amount of Markov models. We highlight this point by showing how multidimensional jump SDEs with Lévy driven jump part under different coefficient assumptions can be seamlessly integrated into our framework, thus establishing novel adaptive sup-norm estimation rates for this class of processes."]]></description>
<dc:subject>to:NB to_read markov_models minimax empirical_processes statistical_inference_for_stochastic_processes re:almost_none mixing statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:60fea291f30b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:minimax"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:almost_none"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1901.08478">
    <title>[1901.08478] Large-deviation principles of switching Markov processes via Hamilton-Jacobi equations</title>
    <dc:date>2021-06-10T02:19:56+00:00</dc:date>
    <link>https://arxiv.org/abs/1901.08478</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We prove pathwise large-deviation principles of switching Markov processes by exploiting the connection to associated Hamilton-Jacobi equations, following Jin Feng's and Thomas Kurtz's method. In the limit that we consider, we show how the large-deviation problem in path-space reduces to a spectral problem of finding principal eigenvalues. The large-deviation rate functions are given in action-integral form.
"As an application, we demonstrate how macroscopic transport properties of stochastic models of molecular motors can be deduced from an associated principal-eigenvalue problem. The precise characterization of the macroscopic velocity in terms of principal eigenvalues implies that breaking of detailed balance is necessary for obtaining transport. In this way, we extend and unify existing results about molecular motors and place them in the framework of stochastic processes and large-deviation theory."]]></description>
<dc:subject>to:NB large_deviations markov_models non-equilibrium</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a8ebd869f880/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_deviations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:non-equilibrium"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2106.01645">
    <title>[2106.01645] Rényi Divergence in General Hidden Markov Models</title>
    <dc:date>2021-06-07T03:55:45+00:00</dc:date>
    <link>https://arxiv.org/abs/2106.01645</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this paper, we examine the existence of the Rényi divergence between two time invariant general hidden Markov models with arbitrary positive initial distributions. By making use of a Markov chain representation of the probability distribution for the general hidden Markov model and eigenvalue for the associated Markovian operator, we obtain, under some regularity conditions, convergence of the Rényi divergence. By using this device, we also characterize the Rényi divergence, and obtain the Kullback-Leibler divergence as {\alpha} \rightarrow 1 of the Rényi divergence. Several examples, including the classical finite state hidden Markov models, Markov switching models, and recurrent neural networks, are given for illustration. Moreover, we develop a non-Monte Carlo method that computes the Rényi divergence of two-state Markov switching models via the underlying invariant probability measure, which is characterized by the Fredholm integral equation."]]></description>
<dc:subject>to:NB stochastic_processes markov_models state-space_models information_theory</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:acea15a6abd1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:state-space_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2104.05095">
    <title>[2104.05095] Operational approach to metastability</title>
    <dc:date>2021-05-30T21:06:34+00:00</dc:date>
    <link>https://arxiv.org/abs/2104.05095</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this work, we introduce an information-theoretic approach for considering changes in dynamics of finitely dimensional open quantum systems governed by master equations. This experimentally motivated approach arises from considering how the averages of system observables change with time and quantifies how non-stationary the system is during a given time regime. By drawing an analogy with the exponential decay, we are able to further investigate regimes when such changes are negligible according to the logarithmic scale of time, and thus the system is approximately stationary. While this is always the case within the initial and final regimes of the dynamics, with the system respectively approximated by its initial and asymptotic states, we show that a distinct regime of approximate stationarity may arise. In turn, we establish a quantitative description of the phenomenon of metastability in open quantum systems. The initial relaxation occurring before the corresponding metastable regime and of the long-time dynamics taking place afterwards are also characterised. Furthermore, we explain how metastability relates to the separation in the real part of the master equation spectrum and connect our approach to the spectral theory of metastability, clarifying when the latter follows. All of our general results directly translate to Markovian dynamics of classical stochastic systems."]]></description>
<dc:subject>to:NB stochastic_processes markov_models metastability</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:d94fd43cf4ab/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:metastability"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2104.07798">
    <title>[2104.07798] Memory Order Decomposition of Symbolic Sequences</title>
    <dc:date>2021-04-19T14:39:06+00:00</dc:date>
    <link>https://arxiv.org/abs/2104.07798</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We introduce a general method for the study of memory in symbolic sequences based on higher-order Markov analysis. The Markov process that best represents a sequence is expressed as a mixture of matrices of minimal orders, enabling the definition of the so-called memory profile, which unambiguously reflects the true order of correlations. The method is validated by recovering the memory profiles of tunable synthetic sequences. Finally, we scan real data and showcase with practical examples how our protocol can be used to extract relevant stochastic properties of symbolic sequences."

--- Very interested to see if there's any mention of context trees, variable-order Markov chains, etc., let alone sofic processes.]]></description>
<dc:subject>to:NB to_read re:AoS_project markov_models latora.vito symbolic_dynamics color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:87b194c2d04a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:latora.vito"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:symbolic_dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:color_me_skeptical"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.cambridge.org/core/journals/journal-of-applied-probability/article/abs/simple-conditions-for-metastability-of-continuous-markov-chains/6EF80575C90D4DF6288943EAD4883D84">
    <title>Simple conditions for metastability of continuous Markov chains | Journal of Applied Probability | Cambridge Core</title>
    <dc:date>2021-04-14T20:08:54+00:00</dc:date>
    <link>https://www.cambridge.org/core/journals/journal-of-applied-probability/article/abs/simple-conditions-for-metastability-of-continuous-markov-chains/6EF80575C90D4DF6288943EAD4883D84</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["A family  of Markov chains is said to exhibit metastable mixing with modes  if its spectral gap (or some other mixing property) is very close to the worst conductance  of its modes for all large values of . We give simple sufficient conditions for a family of Markov chains to exhibit metastability in this sense, and verify that these conditions hold for a prototypical Metropolis–Hastings chain targeting a mixture distribution. The existing metastability literature is large, and our present work is aimed at filling the following small gap: finding sufficient conditions for metastability that are easy to verify for typical examples from statistics using well-studied methods, while at the same time giving an asymptotically exact formula for the spectral gap (rather than a bound that can be very far from sharp). Our bounds from this paper are used in a companion paper (O. Mangoubi, N. S. Pillai, and A. Smith, arXiv:1808.03230) to compare the mixing times of the Hamiltonian Monte Carlo algorithm and a random walk algorithm for multimodal target distributions."]]></description>
<dc:subject>to:NB stochastic_processes markov_models monte_carlo metastability</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4a3bb1a7347c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:monte_carlo"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:metastability"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1705.06040">
    <title>[1705.06040] Information Geometry Approach to Parameter Estimation in Hidden Markov Models</title>
    <dc:date>2021-04-12T03:18:56+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.06040</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the estimation of the transition matrix of a hidden Markovian process by using information geometry with respect to transition matrices. In this paper, only the histogram of k-memory data is used for the estimation. To establish our method, we focus on a partial observation model with the Markovian process and we propose an efficient estimator whose asymptotic estimation error is given as the inverse of projective Fisher information of transition matrices. This estimator is applied to the estimation of the transition matrix of the hidden Markovian process. In this application, we carefully discuss the equivalence problem for hidden Markovian process on the tangent space."]]></description>
<dc:subject>to:NB markov_models information_geometry</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c684c66b0f32/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_geometry"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2009.12287">
    <title>[2009.12287] Large deviations for Markov processes with stochastic resetting : analysis via the empirical density and flows or via excursions between resets</title>
    <dc:date>2021-04-12T03:00:12+00:00</dc:date>
    <link>https://arxiv.org/abs/2009.12287</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Markov processes with stochastic resetting towards the origin generically converge towards non-equilibrium steady-states. Long dynamical trajectories can be thus analyzed via the large deviations at Level 2.5 for the joint probability of the empirical density and the empirical flows, or via the large deviations of semi-Markov processes for the empirical density of excursions between consecutive resets. The large deviations properties of general time-additive observables involving the position and the increments of the dynamical trajectory are then analyzed in terms of the appropriate Markov tilted processes and of the corresponding conditioned processes obtained via the generalization of Doob's h-transform. This general formalism is described in detail for the three possible frameworks, namely discrete-time/discrete-space Markov chains, continuous-time/discrete-space Markov jump processes and continuous-time/continuous-space diffusion processes, and is illustrated with explicit results for the Sisyphus Random Walk and its variants, when the reset probabilities or reset rates are space-dependent."]]></description>
<dc:subject>to:NB markov_models stochastic_processes large_deviations</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:df0b06f5f203/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_deviations"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2101.07290">
    <title>[2101.07290] Finite Markov chains coupled to general Markov processes and an application to metastability II</title>
    <dc:date>2021-01-22T05:57:02+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.07290</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider a diffusion given by a small noise perturbation of a dynamical system driven by a potential function with a finite number of local minima. The classical results of Freidlin and Wentzell show that the time this diffusion spends in the domain of attraction of one of these local minima is approximately exponentially distributed and hence the diffusion should behave approximately like a Markov chain on the local minima. By the work of Bovier and collaborators, the local minima can be associated with the small eigenvalues of the diffusion generator. In Part I of this work, by applying a Markov mapping theorem, we used the eigenfunctions of the generator to couple this diffusion to a Markov chain whose generator has eigenvalues equal to the eigenvalues of the diffusion generator that are associated with the local minima and established explicit formulas for conditional probabilities associated with this coupling. The fundamental question now becomes to relate the coupled Markov chain to the approximate Markov chain suggested by the results of Freidlin and Wentzel. In this paper, we take up this question and provide a complete analysis of this relationship in the special case of a double-well potential in one dimension."]]></description>
<dc:subject>to:NB markov_models stochastic_processes stochastic_differential_equations metastability kurtz.thomas_g.</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0b4d069d0ae8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_differential_equations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:metastability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kurtz.thomas_g."/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1906.03212">
    <title>[1906.03212] Finite Markov chains coupled to general Markov processes and an application to metastability I</title>
    <dc:date>2021-01-22T05:56:38+00:00</dc:date>
    <link>https://arxiv.org/abs/1906.03212</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider a diffusion given by a small noise perturbation of a dynamical system driven by a potential function with a finite number of local minima. The classical results of Freidlin and Wentzell show that the time this diffusion spends in the domain of attraction of one of these local minima is approximately exponentially distributed and hence the diffusion should behave approximately like a Markov chain on the local minima. By the work of Bovier and collaborators, the local minima can be associated with the small eigenvalues of the diffusion generator. Applying a Markov mapping theorem, we use the eigenfunctions of the generator to couple this diffusion to a Markov chain whose generator has eigenvalues equal to the eigenvalues of the diffusion generator that are associated with the local minima and establish explicit formulas for conditional probabilities associated with this coupling. The fundamental question then becomes to relate the coupled Markov chain to the approximate Markov chain suggested by the results of Freidlin and Wentzel. In Part II of this work, we provide a complete analysis of this relationship in the special case of a double-well potential in one dimension. More generally, the coupling can be constructed for a general class of Markov processes and any finite set of eigenvalues of the generator."]]></description>
<dc:subject>to:NB markov_models stochastic_processes stochastic_differential_equations metastability kurtz.thomas_g.</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7c7872cc56c0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_differential_equations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:metastability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kurtz.thomas_g."/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2101.06936">
    <title>[2101.06936] Wasserstein Convergence Rate for Empirical Measures of Markov Chains</title>
    <dc:date>2021-01-19T18:33:59+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.06936</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider a Markov chain on ℝd with invariant measure μ. We are interested in the rate of convergence of the empirical measures towards the invariant measure with respect to the 1-Wasserstein distance. The main result of this article is a new upper bound for the expected Wasserstein distance, which is proved by combining the Kantorovich dual formula with a Fourier expansion. In addition, we show how concentration inequalities around the mean can be obtained."]]></description>
<dc:subject>to:NB markov_models empirical_processes concentration_of_measure stochastic_processes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f9a9a23f65e4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:empirical_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:concentration_of_measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2101.03801">
    <title>[2101.03801] Hidden Markov chains and fields with observations in Riemannian manifolds</title>
    <dc:date>2021-01-12T22:39:27+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.03801</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Hidden Markov chain, or Markov field, models, with observations in a Euclidean space, play a major role across signal and image processing. The present work provides a statistical framework which can be used to extend these models, along with related, popular algorithms (such as the Baum-Welch algorithm), to the case where the observations lie in a Riemannian manifold. It is motivated by the potential use of hidden Markov chains and fields, with observations in Riemannian manifolds, as models for complex signals and images."]]></description>
<dc:subject>to:NB markov_models state-space_models random_fields statistics_on_manifolds</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b0b4911debdd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:state-space_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:random_fields"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics_on_manifolds"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12583?campaign=wolacceptedarticle">
    <title>On some basic features of strictly stationary, reversible Markov chains - Bradley - - Journal of Time Series Analysis - Wiley Online Library</title>
    <dc:date>2021-01-10T19:43:19+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/abs/10.1111/jtsa.12583?campaign=wolacceptedarticle</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["It has been well known for some time that for strictly stationary Markov chains that are “reversible", the special symmetry (with the distribution of the Markov chain as a whole being invariant under a reversal of the “direction of time") provides special extra features in the mathematical theory. This paper here is in part an exposition of some of the basic aspects of that special theory. The mathematical techniques employed in this review are relatively gentle, involving only some basic measure‐theoretic probability theory. To that special theory, a couple of new results are contributed here that are connected with the Rosenblatt strong mixing condition; and those new results in turn assist in bringing further clarity to the exposition of the theory."]]></description>
<dc:subject>to:NB stochastic_processes markov_models mixing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:34be5d457c2b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:mixing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2101.02002">
    <title>[2101.02002] On the Feller-Dynkin and the Martingale Property of One-Dimensional Diffusions</title>
    <dc:date>2021-01-07T21:45:47+00:00</dc:date>
    <link>https://arxiv.org/abs/2101.02002</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We show that a one-dimensional regular continuous strong Markov process \(X\) with scale function \(s\) is a Feller-Dynkin process precisely if the space transformed process \(s (X)\) is a martingale when stopped at the boundaries of its state space. As a consequence, the Feller-Dynkin and the martingale property are equivalent for regular diffusions on natural scale with open state space. Furthermore, for Itô diffusions we discuss relations to existence and uniqueness properties of Cauchy problems, and we identify the infinitesimal generator."]]></description>
<dc:subject>to:NB stochastic_processes markov_models martingales re:almost_none</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1d920b25cb18/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:martingales"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:almost_none"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.12917">
    <title>[2012.12917] Nonparametric approximation of conditional expectation operators</title>
    <dc:date>2020-12-26T05:31:52+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.12917</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Given a regular version of the joint distribution of two random variables X,Y on some second countable locally compact Hausdorff space, we investigate the statistical approximation of the L2-operator defined by [Pf](x):=𝔼[f(Y)∣X=x] under minimal assumptions. By modifying its domain, we prove that P can be arbitrarily well approximated in operator norm by Hilbert--Schmidt operators acting on a reproducing kernel Hilbert space. This fact allows to estimate P uniformly by finite-rank operators over a dense subspace even when P is not compact. In terms of modes of convergence, we thereby obtain the superiority of kernel-based techniques over classically used parametric projection approaches such as Galerkin methods. This also provides a novel perspective on which limiting object the nonparametric estimate of P converges to. As an application, we show that these results are particularly important for a large family of spectral analysis techniques for Markov transition operators. Our investigation also gives a new asymptotic perspective on the so-called kernel conditional mean embedding, which is the theoretical foundation of a wide variety of techniques in kernel-based nonparametric inference."]]></description>
<dc:subject>to:NB probability hilbert_space kernel_estimators markov_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:a69b6cfce1b3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:probability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hilbert_space"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kernel_estimators"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://journals.sagepub.com/doi/abs/10.1177/0049124118782541">
    <title>Expanding the Markov Chain Toolbox: Distributions of Occupation Times and Waiting Times - Christian Dudel, 2018</title>
    <dc:date>2020-12-16T20:18:43+00:00</dc:date>
    <link>https://journals.sagepub.com/doi/abs/10.1177/0049124118782541</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Markov models are important tools for quantitative social research. In this article, new methods for discrete Markov chains are presented. These methods allow us to calculate the distribution of the occupation time in a subset of the state space, the distribution of the waiting time to first entry into a subset of the state space, and the distribution of the waiting time to final exit from a subset of the state space. To demonstrate the usefulness of these methods, we apply them to working life tables for Spanish males to assess how the recent financial crisis affected the length of working life. The results show that the duration of working life decreased considerably, a pattern that can largely be explained by later entry to and earlier exit from the labor market. The findings also indicate that inequality in the length of working life increased."]]></description>
<dc:subject>to:NB markov_models stochastic_processes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:cac2b551ff60/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.07954">
    <title>[2012.07954] Classification and threshold dynamics of stochastic reaction networks</title>
    <dc:date>2020-12-16T17:45:04+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.07954</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Stochastic reaction networks (SRNs) provide models of many real-world networks. Examples include networks in epidemiology, pharmacology, genetics, ecology, chemistry, and social sciences. Here, we model stochastic reaction networks by continuous time Markov chains (CTMCs) and derive new results on the decomposition of the ambient space ℕd0 (with d≥1 the number of species) into communicating classes. In particular, we propose to study (minimal) core networks of an SRN, and show that these characterize the decomposition of the ambient space.
"Special attention is given to one-dimensional mass-action SRNs (1-d stoichiometric subspace). In terms of (up to) four parameters, we provide sharp checkable criteria for various dynamical properties (including explosivity, recurrence, ergodicity, and the tail asymptotics of stationary or quasi-stationary distributions) of SRNs in the sense of their underlying CTMCs. As a result, we prove that all 1-d endotactic networks are non-explosive, and positive recurrent with an ergodic stationary distribution with Conley-Maxwell-Poisson (CMP)-like tail, provided they are essential. In particular, we prove the recently proposed positive recurrence conjecture in one dimension: Weakly reversible mass-action SRNs with 1-d stoichiometric subspaces are positive recurrent. The proofs of the main results rely on our recent work on CTMCs with polynomial transition rate functions."]]></description>
<dc:subject>to:NB stochastic_processes markov_models compartment_models wiuf.carsten</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:16ab5c567d43/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:compartment_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:wiuf.carsten"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://sociologicalscience.com/articles-v7-20-487/">
    <title>Generalized Markovian Quantity Distribution Systems: Social Science Applications | Sociological Science</title>
    <dc:date>2020-12-16T14:47:51+00:00</dc:date>
    <link>https://sociologicalscience.com/articles-v7-20-487/</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose a model of Markovian quantity flows on connected networks that relaxes several properties of the standard compartmental Markov process. The motivation of our generalization are social science applications of the standard model that do not comport with its steady state predictions. The proposed generalization relaxes the predictions that every node belonging to the same nontrivial strong component of a network must acquire the same fraction of its members’ initial quantities and that the sink component(s) of the network must absorb all of the system’s available initial quantity. For example, when applied to refugee flows from a nation in chaos to other nations on a network with one or more sink nations, the standard model predicts that all the refugees will be eventually located in the sink(s) of the network and none that will permanently locate themselves in the nations along the paths to the sink(s). We illustrate this and several other social science applications to which our proposed model is applicable."

--- Last tag because I suspect they're just increasing the number of compartments.]]></description>
<dc:subject>to:NB markov_models compartment_models dynamics_on_networks to_read color_me_skeptical</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:268e76410023/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:compartment_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:dynamics_on_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:color_me_skeptical"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1607677244">
    <title>Sanders , Proutière , Yun : Clustering in Block Markov Chains</title>
    <dc:date>2020-12-11T17:26:24+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1607677244</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper considers cluster detection in Block Markov Chains (BMCs). These Markov chains are characterized by a block structure in their transition matrix. More precisely, the nn possible states are divided into a finite number of KK groups or clusters, such that states in the same cluster exhibit the same transition rates to other states. One observes a trajectory of the Markov chain, and the objective is to recover, from this observation only, the (initially unknown) clusters. In this paper, we devise a clustering procedure that accurately, efficiently and provably detects the clusters. We first derive a fundamental information-theoretical lower bound on the detection error rate satisfied under any clustering algorithm. This bound identifies the parameters of the BMC, and trajectory lengths, for which it is possible to accurately detect the clusters. We next develop two clustering algorithms that can together accurately recover the cluster structure from the shortest possible trajectories, whenever the parameters allow detection. These algorithms thus reach the fundamental detectability limit, and are optimal in that sense."]]></description>
<dc:subject>to:NB markov_models statistical_inference_for_stochastic_processes clustering statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7c12332b27bd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.14821">
    <title>[2011.14821] Discovering Causal Structure with Reproducing-Kernel Hilbert Space $ε$-Machines</title>
    <dc:date>2020-12-10T05:27:05+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.14821</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We merge computational mechanics' definition of causal states (predictively-equivalent histories) with reproducing-kernel Hilbert space (RKHS) representation inference. The result is a widely-applicable method that infers causal structure directly from observations of a system's behaviors whether they are over discrete or continuous events or time. A structural representation -- a finite- or infinite-state kernel ϵ-machine -- is extracted by a reduced-dimension transform that gives an efficient representation of causal states and their topology. In this way, the system dynamics are represented by a stochastic (ordinary or partial) differential equation that acts on causal states. We introduce an algorithm to estimate the associated evolution operator. Paralleling the Fokker-Plank equation, it efficiently evolves causal-state distributions and makes predictions in the original data space via an RKHS functional mapping. We demonstrate these techniques, together with their predictive abilities, on discrete-time, discrete-value infinite Markov-order processes generated by finite-state hidden Markov models with (i) finite or (ii) uncountably-infinite causal states and (iii) a continuous-time, continuous-value process generated by a thermally-driven chaotic flow. The method robustly estimates causal structure in the presence of varying external and measurement noise levels."]]></description>
<dc:subject>to:NB stochastic_processes markov_models prediction prediction_processes hilbert_space kith_and_kin crutchfield.james_p. to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ad432232e8fa/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hilbert_space"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:crutchfield.james_p."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1703.06447">
    <title>[1703.06447] Persistence exponents in Markov chains</title>
    <dc:date>2020-12-10T04:11:03+00:00</dc:date>
    <link>https://arxiv.org/abs/1703.06447</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We prove the existence of the persistence exponent
logλ:=limn→∞1nlogℙμ(X0∈S,…,Xn∈S)
for a class of time homogeneous Markov chains {Xi}i≥0 taking values in a Polish space, where S is a Borel measurable set and μ is an initial distribution. Focusing on the case of AR(p) and MA(q) processes with p,q∈ℕ and continuous innovation distribution, we study the existence of λ and its continuity in the parameters of the AR and MA processes, respectively, for S=ℝ≥0. For AR processes with log-concave innovation distribution, we prove the strict monotonicity of λ. Finally, we compute new explicit exponents in several concrete examples."]]></description>
<dc:subject>to:NB stochastic_processes markov_models large_deviations</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:bfbb37e4d404/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:large_deviations"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2012.02303">
    <title>[2012.02303] Decentralized State-Dependent Markov Chain Synthesis for Swarm Guidance</title>
    <dc:date>2020-12-07T15:28:12+00:00</dc:date>
    <link>https://arxiv.org/abs/2012.02303</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This paper introduces a decentralized state-dependent Markov chain synthesis method for probabilistic swarm guidance of a large number of autonomous agents to a desired steady-state distribution. The probabilistic swarm guidance approach is based on using a Markov chain that determines the transition probabilities of agents to transition from one state to another while satisfying prescribed transition constraints and converging to a desired steady-state distribution. Our main contribution is to develop a decentralized approach to the Markov chain synthesis that updates the underlying column stochastic Markov matrix as a function of the state, i.e., the current swarm probability distribution. Having a decentralized synthesis method eliminates the need to have complex communication architecture. Furthermore, the proposed method aims to cause a minimal number of state transitions to minimize resource usage while guaranteeing convergence to the desired distribution. It is also shown that the convergence rate is faster when compared with previously proposed methodologies."]]></description>
<dc:subject>to:NB distributed_systems control_theory_and_control_engineering markov_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:043e1290163d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:distributed_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:control_theory_and_control_engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/chapter/10.1007/978-3-030-35902-7_9">
    <title>Revisiting Markov Models of Intragenerational Social Mobility | SpringerLink</title>
    <dc:date>2020-12-07T15:18:38+00:00</dc:date>
    <link>https://link.springer.com/chapter/10.1007/978-3-030-35902-7_9</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We generalize stochastic models of occupational mobility introduced in sociology to develop computational models of social and economic mobility under socio-economic constraints. In spite of simplifying assumptions, these models capture many of the essential mechanisms underlying the phenomena under focus. We argue that a more mechanism-based approach driven by underlying social theory may augment the predominantly problem-solving centric approaches in computational social science."]]></description>
<dc:subject>to:NB to_read markov_models sociology inequality to_teach:data_over_space_and_time rvenkat</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:2be4b1b806de/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:sociology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:inequality"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data_over_space_and_time"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:rvenkat"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.14994">
    <title>[2011.14994] Reformulating non-equilibrium steady-states and generalised Hopfield discrimination</title>
    <dc:date>2020-12-02T01:46:44+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.14994</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Markov processes are widely used to model stochastic systems in physics and biology. Their steady-state (s.s.) probabilities are given in terms of their transition rates by the Matrix-Tree theorem (MTT). The MTT uses spanning trees in a graph-theoretic representation of the system and reveals that, away from thermodynamic equilibrium, s.s. probabilities become globally dependent on all transition rates and the resulting expressions grow super-exponentially in the graph size. The overwhelming complexity and lack of thermodynamic insight have impeded analysis, despite substantial progress elsewhere in non-equilibrium physics. Assuming Arrhenius rates with vertex energies and edge barrier energies, we show that the s.s. probability of vertex i is proportional to the average of exp(−S(P)), where S(P) is the entropy generated along a minimal path, P, from i to a reference vertex. The average is taken over a Boltzmann-like probability distribution on spanning trees, whose ``energies'' are their total edge barrier energies. This reformulation offers a thermodynamic interpretation that smoothly generalises equilibrium statistical mechanics and it reorganises the expression complexity: the number of distinct minimal-path entropies depends on the number of edges where energy is expended, not on graph size. We demonstrate the power of this reformulation by extending Hopfield's analysis of discrimination by kinetic proofreading to any graph in which energy is expended at only one edge, for which we derive a general formula for the s.s. error ratio."]]></description>
<dc:subject>to:NB statistical_mechanics non-equilibrium markov_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:912c49235927/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_mechanics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:non-equilibrium"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.14664">
    <title>[2011.14664] Markov and almost Markov properties in one, two or more directions</title>
    <dc:date>2020-12-02T01:43:04+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.14664</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["In this review-type paper written at the occasion of the Oberwolfach workshop {\em One-sided vs. Two-sided stochastic processes} (february 22-29, 2020), we discuss and compare Markov properties and generalisations thereof in more directions, as well as weaker forms of conditional dependence, again either in one or more directions. In particular, we discuss in both contexts various extensions of Markov chains and Markov fields and their properties, such as g-measures, Variable Length Markov Chains, Variable Neighbourhood Markov Fields, Variable Neighbourhood (Parsimonious) Random Fields, and Generalized Gibbs Measures"]]></description>
<dc:subject>to:NB stochastic_processes markov_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:b0f44a064e72/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.10985">
    <title>[2011.10985] A universal probability approximation method: Markov process approach</title>
    <dc:date>2020-11-30T04:02:00+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.10985</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We view the classical Lindeberg principle in a Markov process setting to establish a universal probability approximation framework by Itô's formula and Markov semigroup. As applications, we consider approximating a family of online stochastic gradient descents (SGDs) by a stochastic differential equation (SDE) driven by additive Brownian motion, and obtain an approximation error with explicit dependence on the dimension which makes it possible to analyse high dimensional models. We also apply our framework to study stable approximation and normal approximation and obtain their optimal convergence rates (up to a logarithmic correction for normal approximation)."]]></description>
<dc:subject>markov_models convergence_of_stochastic_processes stochastic_processes stochastic_differential_equations approximation stochastic_gradient_descent in_NB</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:c3a1ccd774e2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:convergence_of_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_differential_equations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_gradient_descent"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1907.00113">
    <title>[1907.00113] Learning Markov models via low-rank optimization</title>
    <dc:date>2020-11-30T03:59:56+00:00</dc:date>
    <link>https://arxiv.org/abs/1907.00113</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Modeling unknown systems from data is a precursor of system optimization and sequential decision making. In this paper, we focus on learning a Markov model from a single trajectory of states. Suppose that the transition model has a small rank despite of having a large state space, meaning that the system admits a low-dimensional latent structure. We show that one can estimate the full transition model accurately using a trajectory of length that is proportional to the total number of states. We propose two maximum likelihood estimation methods: a convex approach with nuclear-norm regularization and a nonconvex approach with rank constraint. We explicitly derive the statistical rates of both estimators in terms of the Kullback-Leiber divergence and the ℓ2 error and also establish a minimax lower bound to assess the tightness of these rates. For computing the nonconvex estimator, we develop a novel DC (difference of convex function) programming algorithm that starts with the convex M-estimator and then successively refines the solution till convergence. Empirical experiments demonstrate consistent superiority of the nonconvex estimator over the convex one."

--- Couldn't this be accomplished more simply by using the results about parameterized Markov chains in Billingsley (1961)?  (I guess Billingsley didn't worry about actually finding the optimum.)]]></description>
<dc:subject>to:NB low-rank_approximation markov_models statistics optimization statistical_inference_for_stochastic_processes</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7c5dd99517e8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:low-rank_approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2011.13780">
    <title>[2011.13780] Rate of convergence in Trotter's approximation theorem and its applications</title>
    <dc:date>2020-11-30T03:02:09+00:00</dc:date>
    <link>https://arxiv.org/abs/2011.13780</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The celebrated Trotter approximation theorem provides a sufficient condition for the convergence of a sequence of operator semigroups in terms of the corresponding sequence of infinitesimal generators. There exists a few results on the rate of convergence in Trotter's theorem under some constraints. In the present paper, a new rate of convergence in Trotter's theorem with full generality is given. Moreover, we see that this rate of convergence works well to obtain quantitative estimates for some limit theorems in probability theory."]]></description>
<dc:subject>to:NB markov_models convergence_of_stochastic_processes stochastic_processes re:almost_none approximation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:df4597d34e61/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:convergence_of_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:almost_none"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:approximation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2005.06623">
    <title>[2005.06623] Kernel Analog Forecasting: Multiscale Test Problems</title>
    <dc:date>2020-11-25T14:36:08+00:00</dc:date>
    <link>https://arxiv.org/abs/2005.06623</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Data-driven prediction is becoming increasingly widespread as the volume of data available grows and as algorithmic development matches this growth. The nature of the predictions made, and the manner in which they should be interpreted, depends crucially on the extent to which the variables chosen for prediction are Markovian, or approximately Markovian. Multiscale systems provide a framework in which this issue can be analyzed. In this work kernel analog forecasting methods are studied from the perspective of data generated by multiscale dynamical systems. The problems chosen exhibit a variety of different Markovian closures, using both averaging and homogenization; furthermore, settings where scale-separation is not present and the predicted variables are non-Markovian, are also considered. The studies provide guidance for the interpretation of data-driven prediction methods when used in practice."]]></description>
<dc:subject>to:NB prediction markov_models time_series to_read macro_from_micro kernel_smoothing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0145978fda9c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:macro_from_micro"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kernel_smoothing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2002.02001">
    <title>[2002.02001] A guide to state-space modeling of ecological time series</title>
    <dc:date>2020-11-23T17:42:40+00:00</dc:date>
    <link>https://arxiv.org/abs/2002.02001</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["State-space models (SSMs) are an important modeling framework for analyzing ecological time series. These hierarchical models are commonly used to model population dynamics, animal movement, and capture-recapture data, and are now increasingly being used to model other ecological processes. SSMs are popular because they are flexible and they model the natural variation in ecological processes separately from observation error. Their flexibility allows ecologists to model continuous, count, binary, and categorical data with linear or nonlinear processes that evolve in discrete or continuous time. Modeling the two sources of stochasticity separately allows researchers to differentiate between biological variation (e.g., in birth processes) and imprecision in the sampling methodology, and generally provides better estimates of the ecological quantities of interest than if only one source of stochasticity is directly modeled. Since the introduction of SSMs, a broad range of fitting procedures have been proposed. However, the variety and complexity of these procedures can limit the ability of ecologists to formulate and fit their own SSMs. We provide the knowledge for ecologists to create SSMs that are robust to common, and often hidden, estimation problems, and the model selection and validation tools that can help them assess how well their models fit their data. In this paper, we present a review of SSMs that will provide a strong foundation to ecologists interested in learning about SSMs, introduce new tools to veteran SSM users, and highlight promising research directions for statisticians interested in ecological applications. The review is accompanied by an in-depth tutorial that demonstrates how SSMs models can be fitted and validated in R. Together, the review and tutorial present an introduction to SSMs that will help ecologists to formulate, fit, and validate their models."]]></description>
<dc:subject>to:NB state-space_models markov_models ecology statistics to_teach:data_over_space_and_time</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:176ad5a8bc65/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:state-space_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ecology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data_over_space_and_time"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://onlinelibrary.wiley.com/doi/full/10.1002/env.1102?casa_token=ocbU79FU42EAAAAA%3AQDyFS0-w-z1X4iyTEguPeij1WKqyFlab8iL4qHNhaVg8STIrrUbdwgliDave2STG6TP7Ue6-ZfbM6g">
    <title>Autologistic models for binary data on a lattice - Hughes - 2011 - Environmetrics - Wiley Online Library</title>
    <dc:date>2020-11-21T03:45:52+00:00</dc:date>
    <link>https://onlinelibrary.wiley.com/doi/full/10.1002/env.1102?casa_token=ocbU79FU42EAAAAA%3AQDyFS0-w-z1X4iyTEguPeij1WKqyFlab8iL4qHNhaVg8STIrrUbdwgliDave2STG6TP7Ue6-ZfbM6g</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The autologistic model is a Markov random field model for spatial binary data. Because it can account for both statistical dependence among the data and for the effects of potential covariates, the autologistic model is particularly suitable for problems in many fields, including ecology, where binary responses, indicating the presence or absence of a certain plant or animal species, are observed over a two‐dimensional lattice. We consider inference and computation for two models: the original autologistic model due to Besag, and the centered autologistic model proposed recently by Caragea and Kaiser. Parameter estimation and inference for these models is a notoriously difficult problem due to the complex form of the likelihood function. We study pseudolikelihood (PL), maximum likelihood (ML), and Bayesian approaches to inference and describe ways to optimize the efficiency of these algorithms and the perfect sampling algorithms upon which they depend, taking advantage of parallel computing when possible. We conduct a simulation study to investigate the effects of spatial dependence and lattice size on parameter inference, and find that inference for regression parameters in the centered model is reliable only for reasonably large lattices (n > 900) and no more than moderate spatial dependence. When the lattice is large enough, and the dependence small enough, to permit reliable inference, the three approaches perform comparably, and so we recommend the PL approach for its easier implementation and much faster execution."]]></description>
<dc:subject>to:NB random_fields ecology spatial_statistics birds markov_models ising_model logistic_regression to_teach:data_over_space_and_time of_course_its_really_a_spin_glass have_skimmed</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:f06130584e87/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:random_fields"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ecology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:spatial_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:birds"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ising_model"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:logistic_regression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data_over_space_and_time"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:of_course_its_really_a_spin_glass"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_skimmed"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1198/108571105X46543">
    <title>Modeling spatial-temporal binary data using Markov random fields | SpringerLink</title>
    <dc:date>2020-11-21T03:42:14+00:00</dc:date>
    <link>https://link.springer.com/article/10.1198/108571105X46543</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["An autologistic regression model consists of a logistic regression of a response variable on explanatory variables and an autoregression on responses at neighboring locations on a lattice. It is a Markov random field with pairwise spatial dependence and is a popular tool for modeling spatial binary responses. In this article, we add a temporal component to the autologistic regression model for spatial-temporal binary data. The spatial-temporal autologistic regression model captures the relationship between a binary response and potential explanatory variables, and adjusts for both spatial dependence and temporal dependence simultaneously by a space-time Markov random field. We estimate the model parameters by maximum pseudo-likelihood and obtain optimal prediction of future responses on the lattice by a Gibbs sampler. For illustration, the method is applied to study the outbreaks of southern pine bettle in North Carolina. We also discuss the generality of our approach for modeling other types of spatial-temporal lattice data."]]></description>
<dc:subject>to:NB spatio-temporal_statistics random_fields markov_models insects have_skimmed to_teach:data_over_space_and_time of_course_its_really_a_spin_glass ising_model logistic_regression</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:01152ca5b0a6/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:spatio-temporal_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:random_fields"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:insects"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_skimmed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data_over_space_and_time"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:of_course_its_really_a_spin_glass"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ising_model"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:logistic_regression"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://link.springer.com/article/10.1023/A:1018553807765">
    <title>Modelling the distribution of plant species using the autologistic regression model | SpringerLink</title>
    <dc:date>2020-11-21T03:41:58+00:00</dc:date>
    <link>https://link.springer.com/article/10.1023/A:1018553807765</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["For modeling the distribution of plant species in terms of climate covariates, we consider an autologistic regression model for spatial binary data on a regularly spaced lattice. This model belongs to the class of autologistic models introduced by Besag (1974). Three estimation methods, the coding method, maximum pseudolikelihood method and Markov chain Monte Carlo method are studied and comparedvia simulation and real data examples. As examples, we use the proposed methodology to model the distributions of two plant species in the state of Florida."]]></description>
<dc:subject>to:NB ecology spatial_statistics markov_models random_fields have_skimmed to_teach:data_over_space_and_time of_course_its_really_a_spin_glass ising_model logistic_regression</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:1e0bc6629a0a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ecology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:spatial_statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:random_fields"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_skimmed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data_over_space_and_time"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:of_course_its_really_a_spin_glass"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:ising_model"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:logistic_regression"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.bj/1605841254">
    <title>Wolfer , Kontorovich : Statistical estimation of ergodic Markov chain kernel over discrete state space</title>
    <dc:date>2020-11-20T04:03:29+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.bj/1605841254</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We investigate the statistical complexity of estimating the parameters of a discrete-state Markov chain kernel from a single long sequence of state observations. In the finite case, we characterize (modulo logarithmic factors) the minimax sample complexity of estimation with respect to the operator infinity norm, while in the countably infinite case, we analyze the problem with respect to a natural entry-wise norm derived from total variation. We show that in both cases, the sample complexity is governed by the mixing properties of the unknown chain, for which, in the finite-state case, there are known finite-sample estimators with fully empirical confidence intervals."]]></description>
<dc:subject>to:NB markov_models statistical_inference_for_stochastic_processes kith_and_kin kontorovich.aryeh</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3b6d2a8bf1e0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kontorovich.aryeh"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1600480925">
    <title>Fauß , Zoubir , Poor : Minimax optimal sequential hypothesis tests for Markov processes</title>
    <dc:date>2020-11-19T05:30:29+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1600480925</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Under mild Markov assumptions, sufficient conditions for strict minimax optimality of sequential tests for multiple hypotheses under distributional uncertainty are derived. First, the design of optimal sequential tests for simple hypotheses is revisited, and it is shown that the partial derivatives of the corresponding cost function are closely related to the performance metrics of the underlying sequential test. Second, an implicit characterization of the least favorable distributions for a given testing policy is stated. By combining the results on optimal sequential tests and least favorable distributions, sufficient conditions for a sequential test to be minimax optimal under general distributional uncertainties are obtained. The cost function of the minimax optimal test is further identified as a generalized ff-dissimilarity and the least favorable distributions as those that are most similar with respect to this dissimilarity. Numerical examples for minimax optimal sequential tests under different uncertainties illustrate the theoretical results."]]></description>
<dc:subject>to:NB hypothesis_testing markov_models stochastic_processes statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:db42efc7de75/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:hypothesis_testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://projecteuclid.org/euclid.aos/1594972821">
    <title>Dieuleveut , Durmus , Bach : Bridging the gap between constant step size stochastic gradient descent and Markov chains</title>
    <dc:date>2020-11-18T21:47:12+00:00</dc:date>
    <link>https://projecteuclid.org/euclid.aos/1594972821</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We consider the minimization of a strongly convex objective function given access to unbiased estimates of its gradient through stochastic gradient descent (SGD) with constant step size. While the detailed analysis was only performed for quadratic functions, we provide an explicit asymptotic expansion of the moments of the averaged SGD iterates that outlines the dependence on initial conditions, the effect of noise and the step size, as well as the lack of convergence in the general (nonquadratic) case. For this analysis we bring tools from Markov chain theory into the analysis of stochastic gradient. We then show that Richardson–Romberg extrapolation may be used to get closer to the global optimum, and we show empirical improvements of the new extrapolation scheme."]]></description>
<dc:subject>markov_models stochastic_processes optimization stochastic_gradient_descent in_NB bach.francis</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:0a733827e7de/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_gradient_descent"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:bach.francis"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://ieeexplore.ieee.org/document/8804216">
    <title>Analyticity of Entropy Rates of Continuous-State Hidden Markov Models - IEEE Journals &amp; Magazine</title>
    <dc:date>2020-11-16T16:02:36+00:00</dc:date>
    <link>https://ieeexplore.ieee.org/document/8804216</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["The analyticity of the entropy and relative entropy rates of continuous-state hidden Markov models is studied here. Using the analytic continuation principle and the stability properties of the optimal filter, the analyticity of these rates is established for analytically parameterized models. The obtained results hold under relatively mild conditions and cover several useful classes of hidden Markov models. These results are relevant for several theoretically and practically important problems arising in statistical inference, system identification and information theory."]]></description>
<dc:subject>to:NB entropy information_theory markov_models state-space_models doucet.arnaud</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:9e84242609c9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:entropy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:state-space_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:doucet.arnaud"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1912.00401">
    <title>[1912.00401] Long-time asymptotics of stochastic reaction systems</title>
    <dc:date>2020-11-15T21:14:02+00:00</dc:date>
    <link>https://arxiv.org/abs/1912.00401</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We study the stochastic dynamics of a system of interacting species in a stochastic environment by means of a continuous-time Markov chain with transition rates depending on the state of the environment. Models of gene regulation in systems biology take this form. We characterise the finite-time distribution of the Markov chain, provide conditions for ergodicity, and characterise the stationary distribution (when it exists) as a mixture of Poisson distributions. The mixture measure is uniquely identified as the law of a fixed point of a stochastic recurrence equation. This recursion is crucial for statistical computation of moments and other distributional features."]]></description>
<dc:subject>to:NB stochastic_processes markov_models biochemical_networks to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3c8dfed1a256/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:biochemical_networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1607.07570">
    <title>[1607.07570] Random graph models for dynamic networks</title>
    <dc:date>2020-07-15T15:37:53+00:00</dc:date>
    <link>https://arxiv.org/abs/1607.07570</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose generalizations of a number of standard network models, including the classic random graph, the configuration model, and the stochastic block model, to the case of time-varying networks. We assume that the presence and absence of edges are governed by continuous-time Markov processes with rate parameters that can depend on properties of the nodes. In addition to computing equilibrium properties of these models, we demonstrate their use in data analysis and statistical inference, giving efficient algorithms for fitting them to observed network data. This allows us, for instance, to estimate the time constants of network evolution or infer community structure from temporal network data using cues embedded both in the probabilities over time that node pairs are connected by edges and in the characteristic dynamics of edge appearance and disappearance. We illustrate our methods with a selection of applications, both to computer-generated test networks and real-world examples."]]></description>
<dc:subject>to:NB heard_the_talk network_data_analysis markov_models kith_and_kin moore.cristopher newman.mark networks_in_and_over_time</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:3e41f2daf2a9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:heard_the_talk"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:network_data_analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:kith_and_kin"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:moore.cristopher"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:newman.mark"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:networks_in_and_over_time"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2005.03750">
    <title>[2005.03750] Inference, Prediction, and Entropy-Rate Estimation of Continuous-time, Discrete-event Processes</title>
    <dc:date>2020-05-29T13:38:49+00:00</dc:date>
    <link>https://arxiv.org/abs/2005.03750</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Inferring models, predicting the future, and estimating the entropy rate of discrete-time, discrete-event processes is well-worn ground. However, a much broader class of discrete-event processes operates in continuous-time. Here, we provide new methods for inferring, predicting, and estimating them. The methods rely on an extension of Bayesian structural inference that takes advantage of neural network's universal approximation power. Based on experiments with complex synthetic data, the methods are competitive with the state-of-the-art for prediction and entropy-rate estimation."]]></description>
<dc:subject>to:NB to_read prediction markov_models statistical_inference_for_stochastic_processes crutchfield.james_p. entropy_estimation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:01310a468c03/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:crutchfield.james_p."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:entropy_estimation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.mdpi.com/1099-4300/11/3/385">
    <title>Entropy | Free Full-Text | Properties of the Statistical Complexity Functional and Partially Deterministic HMMs</title>
    <dc:date>2020-05-16T17:46:39+00:00</dc:date>
    <link>https://www.mdpi.com/1099-4300/11/3/385</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Statistical complexity is a measure of complexity of discrete-time stationary stochastic processes, which has many applications. We investigate its more abstract properties as a non-linear function of the space of processes and show its close relation to the Knight’s prediction process. We prove lower semi-continuity, concavity, and a formula for the ergodic decomposition of statistical complexity. On the way, we show that the discrete version of the prediction process has a continuous Markov transition. We also prove that, given the past output of a partially deterministic hidden Markov model (HMM), the uncertainty of the internal state is constant over time and knowledge of the internal state gives no additional information on the future output. Using this fact, we show that the causal state distribution is the unique stationary representation on prediction space that may have finite entropy."]]></description>
<dc:subject>to:NB complexity_measures markov_models prediction stochastic_processes to_read re:AoS_project</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7bbb0912fe69/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:complexity_measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.sciencedirect.com/science/article/abs/pii/S0031320305000233?via%3Dihub">
    <title>Links between probabilistic automata and hidden Markov models: probability distributions, learning models and induction algorithms - ScienceDirect</title>
    <dc:date>2020-05-12T23:51:32+00:00</dc:date>
    <link>https://www.sciencedirect.com/science/article/abs/pii/S0031320305000233?via%3Dihub</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["This article presents an overview of Probabilistic Automata (PA) and discrete Hidden Markov Models (HMMs), and aims at clarifying the links between them. The first part of this work concentrates on probability distributions generated by these models. Necessary and sufficient conditions for an automaton to define a probabilistic language are detailed. It is proved that probabilistic deterministic automata (PDFA) form a proper subclass of probabilistic non-deterministic automata (PNFA). Two families of equivalent models are described next. On one hand, HMMs and PNFA with no final probabilities generate distributions over complete finite prefix-free sets. On the other hand, HMMs with final probabilities and probabilistic automata generate distributions over strings of finite length. The second part of this article presents several learning models, which formalize the problem of PA induction or, equivalently, the problem of HMM topology induction and parameter estimation. These learning models include the PAC and identification with probability 1 frameworks. Links with Bayesian learning are also discussed. The last part of this article presents an overview of induction algorithms for PA or HMMs using state merging, state splitting, parameter pruning and error-correcting techniques."]]></description>
<dc:subject>to:NB markov_models automata_theory to_read re:AoS_project</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:4432b2e40b08/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:automata_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/math/0606591">
    <title>[math/0606591] Approximation of stationary processes by Hidden Markov Models</title>
    <dc:date>2020-05-12T23:48:53+00:00</dc:date>
    <link>https://arxiv.org/abs/math/0606591</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We aim at the construction of a Hidden Markov Model (HMM) of assigned complexity (number of states of the underlying Markov chain) which best approximates, in Kullback-Leibler divergence rate, a given stationary process. We establish, under mild conditions, the existence of the divergence rate between a stationary process and an HMM. Since in general there is no analytic expression available for this divergence rate, we approximate it with a properly defined, and easily computable, divergence between Hankel matrices, which we use as our approximation criterion. We propose a three-step algorithm, based on the Nonnegative Matrix Factorization technique, which realizes an HMM optimal with respect to the defined approximation criterion. A full theoretical analysis of the algorithm is given in the special case of Markov approximation."]]></description>
<dc:subject>to:NB approximation stochastic_processes information_theory markov_models re:AoS_project to_read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:7ded2a998ee1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:information_theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:re:AoS_project"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/0912.4480">
    <title>[0912.4480] Consistency of the maximum likelihood estimator for general hidden Markov models</title>
    <dc:date>2020-05-12T23:48:06+00:00</dc:date>
    <link>https://arxiv.org/abs/0912.4480</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Consider a parametrized family of general hidden Markov models, where both the observed and unobserved components take values in a complete separable metric space. We prove that the maximum likelihood estimator (MLE) of the parameter is strongly consistent under a rather minimal set of assumptions. As special cases of our main result, we obtain consistency in a large class of nonlinear state space models, as well as general results on linear Gaussian state space models and finite state models. A novel aspect of our approach is an information-theoretic technique for proving identifiability, which does not require an explicit representation for the relative entropy rate. Our method of proof could therefore form a foundation for the investigation of MLE consistency in more general dependent and non-Markovian time series. Also of independent interest is a general concentration inequality for V-uniformly ergodic Markov chains."]]></description>
<dc:subject>to:NB have_read markov_models statistical_inference_for_stochastic_processes statistics_on_manifolds time_series</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:45a70689d38a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:have_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistical_inference_for_stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics_on_manifolds"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:time_series"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://epubs.siam.org/doi/abs/10.1137/1035003?casa_token=VQ1U2GEJoAUAAAAA:RWor_QJUmKSrKfuGUlp9flVZPu5RhXtsXYLZYpEK-O-ah6MH27i3zyXrPqw3xrY-oOaRyOtzAME">
    <title>Qualitative Theory of Compartmental Systems | SIAM Review | Vol. 35, No. 1 | Society for Industrial and Applied Mathematics</title>
    <dc:date>2020-05-08T17:11:21+00:00</dc:date>
    <link>https://epubs.siam.org/doi/abs/10.1137/1035003?casa_token=VQ1U2GEJoAUAAAAA:RWor_QJUmKSrKfuGUlp9flVZPu5RhXtsXYLZYpEK-O-ah6MH27i3zyXrPqw3xrY-oOaRyOtzAME</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["Dynamic models of many processes in the biological and physical sciences which depend on local mass balance conditions give rise to systems of ordinary differential equations, many nonlinear, that are called compartmental systems. In this paper, the authors define compartmental systems, specify their relations to other nonnegative systems, and discuss examples of applications.
"The authors review the qualitative results on linear and nonlinear compartmental systems, including their relation to cooperative systems. They review the results for linear compartmental systems and then integrate and expand the results on nonlinear compartmental systems, providing a framework for unifying them under a few general theorems. In the course of that they complete the solution of a problem posed by Bellman and show that closed nonlinear, autonomous, n-compartment systems can show the full gamut of possible behaviors of systems of ODES.
"Finally, to provide additional structure to this study, the authors show how to partition compartmental systems of arbitrary connectivities into four basic types and then give the qualitative analysis for autonomous, nonlinear compartmental systems of the four basic types."]]></description>
<dc:subject>to_read markov_models dynamical_systems stochastic_processes simon.carl_p. jacquez.john_a. to_teach:data_over_space_and_time in_NB compartment_models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:ce4faf53ed71/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_read"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:dynamical_systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:stochastic_processes"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:simon.carl_p."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:jacquez.john_a."/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to_teach:data_over_space_and_time"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:in_NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:compartment_models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1911.12198">
    <title>[1911.12198] Strong structure recovery for partially observed discrete Markov random fields on graphs</title>
    <dc:date>2020-01-30T23:52:29+00:00</dc:date>
    <link>https://arxiv.org/abs/1911.12198</link>
    <dc:creator>cshalizi</dc:creator><description><![CDATA["We propose a penalized maximum likelihood criterion to estimate the graph of conditional dependencies in a discrete Markov random field, that can be partially observed. We prove the almost sure convergence of the estimator in the case of a finite or countable infinite set of variables. In the finite case, the underlying graph can be recovered with probability one, while in the countable infinite case we can recover any finite subgraph with probability one, by allowing the candidate neighborhoods to grow with the sample size n. Our method requires minimal assumptions on the probability distribution and contrary to other approaches in the literature, the usual positivity condition is not needed."]]></description>
<dc:subject>to:NB random_fields markov_models statistics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:cshalizi/b:80cc0dfb4787/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:to:NB"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:random_fields"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:markov_models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:cshalizi/t:statistics"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>