Pinboard (arthegall) https://pinboard.in/u:arthegall/public/ recent bookmarks from arthegall "Bad numbers in the "gzip beats BERT" paper?" 2023-07-23T13:50:10+00:00 https://kenschutte.com/gzip-knn-paper/ arthegall gzip-beats-bert compression deep-learning machinelearning funny interesting https://pinboard.in/ https://pinboard.in/u:arthegall/b:d05e24f580bc/ “Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors 2023-07-15T12:08:05+00:00 https://aclanthology.org/2023.findings-acl.426/ arthegallcompression llms machinelearning non-parametric-so-called via:vaguery funny awesome https://pinboard.in/ https://pinboard.in/u:arthegall/b:b0e29e130009/ Corrigan-Gibbs, Boneh, "Prio: Private, Robust, and Scalable Computation of Aggregate Statistics" 2021-05-06T07:54:31+00:00 https://crypto.stanford.edu/prio/paper.pdf arthegall dan-boneh privacy statistics research-article differential-privacy machinelearning https://pinboard.in/ https://pinboard.in/u:arthegall/b:9d29f4dee7e6/ Pereira, Singer, Tishby, "Beyond Word N-Grams" 2021-05-06T07:40:00+00:00 https://aaai.org/Library/BISFAI/1995/bisfai95-019.php arthegall n-grams nlp machinelearning research-article fernando-pereira https://pinboard.in/ https://pinboard.in/u:arthegall/b:57f6e387b8bf/ privacytrustlab/ml_privacy_meter: Machine Learning Privacy Meter: A tool to quantify the privacy risks of machine learning models with respect to inference attacks 2020-08-01T09:54:26+00:00 https://github.com/privacytrustlab/ml_privacy_meter arthegallprivacy differential-privacy software github machinelearning https://pinboard.in/ https://pinboard.in/u:arthegall/b:7a0a6b276cf3/ [2004.03705] Deep Learning Based Text Classification: A Comprehensive Review 2020-07-14T19:09:04+00:00 https://arxiv.org/abs/2004.03705 arthegalldeep-learning review arxiv machinelearning classification nlp https://pinboard.in/ https://pinboard.in/u:arthegall/b:afa899a92fee/ [1706.00754] Computationally and statistically efficient learning of causal Bayes nets using path queries 2020-07-07T11:04:44+00:00 https://arxiv.org/abs/1706.00754 arthegallbayesian-networks arxiv research-article machinelearning causal-networks https://pinboard.in/ https://pinboard.in/u:arthegall/b:5d7a93ffd1a7/ Pedro Domingos et al. "Version Space Algebra and its Application to Programming by Demonstration" 2020-06-11T18:55:18+00:00 https://pdfs.semanticscholar.org/7b8b/40a4c485593a7f4fe6d9596f5ac2d0d1f681.pdf arthegallpdf research-article machinelearning classification pedro-domingos https://pinboard.in/ https://pinboard.in/u:arthegall/b:de7756c22a7f/ Gaussian Processes, not quite for dummies 2020-06-05T20:36:33+00:00 https://thegradient.pub/gaussian-process-not-quite-for-dummies/ arthegallgaussian-processes tutorial machinelearning https://pinboard.in/ https://pinboard.in/u:arthegall/b:a2685e8cdb37/ [1905.10615] Adversarial Policies: Attacking Deep Reinforcement Learning 2020-04-20T15:17:14+00:00 https://arxiv.org/abs/1905.10615 arthegallstuart-russell machinelearning deep-learning adversarial-examples arxiv research-article https://pinboard.in/ https://pinboard.in/u:arthegall/b:fb5710e340e1/ A modern maximum-likelihood theory for high-dimensional logistic regression | PNAS 2020-01-23T18:57:57+00:00 https://www.pnas.org/content/116/29/14516.short arthegallmachinelearning emmanuel-candes logistic-regression pnas research-article regression https://pinboard.in/ https://pinboard.in/u:arthegall/b:ffa04a104a1d/ The Effects of Confounding When Making Automatic Intervention Decisions Using Machine Learning by Carlos Fernández, Foster Provost :: SSRN 2019-12-13T10:59:45+00:00 https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3444678 arthegallvia:arsyed confounding statistics machinelearning causality research-article ssrn sigma https://pinboard.in/ https://pinboard.in/u:arthegall/b:5a9da47dd49d/ [1601.01280] Language to Logical Form with Neural Attention 2019-12-10T13:12:39+00:00 https://arxiv.org/abs/1601.01280 arthegallneural-networks sigma machinelearning research-article arxiv https://pinboard.in/ https://pinboard.in/u:arthegall/b:4639d787cca2/ [1508.01991] Bidirectional LSTM-CRF Models for Sequence Tagging 2019-12-10T13:12:11+00:00 https://arxiv.org/abs/1508.01991 arthegallsequence-analysis lstm neural-networks machinelearning arxiv sigma tagging research-article https://pinboard.in/ https://pinboard.in/u:arthegall/b:d27ddbfe59ab/ rflamary/POT: Python Optimal Transport library 2019-10-29T09:17:14+00:00 https://github.com/rflamary/POT arthegallpython library software github optimal-transport machinelearning https://pinboard.in/ https://pinboard.in/u:arthegall/b:196aef0ae130/ [1910.10871] Preventing Adversarial Use of Datasets through Fair Core-Set Construction 2019-10-26T15:56:43+00:00 https://arxiv.org/abs/1910.10871 arthegallvia:cshalizi adversarial-methods machinelearning arxiv research-article https://pinboard.in/ https://pinboard.in/u:arthegall/b:d0ca37d3b3bd/ [1602.02201] The Rate-Distortion Risk in Estimation from Compressed Data 2019-10-26T15:56:15+00:00 https://arxiv.org/abs/1602.02201 arthegallvia:? compression machinelearning research-article arxiv https://pinboard.in/ https://pinboard.in/u:arthegall/b:b62f3c34e055/ [PDF] Using Word Vectors to Improve Word Alignments for Low Resource Machine Translation - Semantic Scholar 2019-10-26T05:47:48+00:00 https://www.semanticscholar.org/paper/Using-Word-Vectors-to-Improve-Word-Alignments-for-Pourdamghani-Ghazvininejad/8f4bf65a6b62cecc6f7b0ab2489a831d9a44a86d arthegalltranslation nlp word-embeddings machinelearning research-article computational-linguistics https://pinboard.in/ https://pinboard.in/u:arthegall/b:c926c327e04a/ [1910.05992] Pathological spectra of the Fisher information metric and its variants in deep neural networks 2019-10-26T05:47:07+00:00 https://arxiv.org/abs/1910.05992 arthegallshun-ichi-amari arxiv research-article machinelearning deep-learning https://pinboard.in/ https://pinboard.in/u:arthegall/b:67598683e6c7/ [1511.05219] How much does your data exploration overfit? Controlling bias via information usage 2019-10-12T09:41:21+00:00 https://arxiv.org/abs/1511.05219 arthegallstatistics machinelearning via:cshalizi overfitting bias arxiv research-article garden-of-forking-paths https://pinboard.in/u:arthegall/b:2db3b94391b1/ [1910.04618] Universal Adversarial Perturbation for Text Classification 2019-10-12T09:40:24+00:00 https://arxiv.org/abs/1910.04618 arthegallmachinelearning via:cshalizi deep-networks classification nlp text arxiv research-article perturbations https://pinboard.in/u:arthegall/b:0da5fbb4d951/ [1212.6806] Leveraging Sociological Models for Predictive Analytics 2019-10-09T14:06:41+00:00 https://arxiv.org/abs/1212.6806 arthegall sociology arxiv predictions machinelearning networks https://pinboard.in/ https://pinboard.in/u:arthegall/b:a789be833760/ [1901.08113] Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN 2019-10-09T13:13:32+00:00 https://arxiv.org/abs/1901.08113 arthegall to-read arxiv research-article machinelearning deep-learning graphs networks https://pinboard.in/ https://pinboard.in/u:arthegall/b:248dd068ef2c/ All the DAGs from Hernan and Robins' Causal Inference Book 2019-10-07T17:18:16+00:00 https://sgfin.github.io/2019/06/19/Causal-Inference-Book-All-DAGs/ arthegallpearl causality machinelearning list https://pinboard.in/ https://pinboard.in/u:arthegall/b:c0acda49454b/ NLG Group at USC: Publications 2019-10-07T12:26:20+00:00 https://www.isi.edu/projects/nlg/publications arthegall nlp structured-text machinelearning publications list poetry translation https://pinboard.in/ https://pinboard.in/u:arthegall/b:80d374d733ab/ Reconciling modern machine-learning practice and the classical bias–variance trade-off | PNAS 2019-09-14T15:12:46+00:00 https://www.pnas.org/content/116/32/15849 arthegall hmmm statistics machinelearning review-article bias-variance pnas https://pinboard.in/ https://pinboard.in/u:arthegall/b:a4cb726efcb4/ [1706.04692] Bias and high-dimensional adjustment in observational studies of peer effects 2019-07-31T02:44:09+00:00 https://arxiv.org/abs/1706.04692 arthegalldean-eckles machinelearning observational-studies via:twitter statistics arxiv research-article privacy https://pinboard.in/ https://pinboard.in/u:arthegall/b:6a1f2d44e112/ Almost differential privacy - Ted is writing things 2019-06-12T13:48:54+00:00 https://desfontain.es/privacy/almost-differential-privacy.html arthegalldifferential-privacy frank-mcsherry research computerscience machinelearning privacy https://pinboard.in/ https://pinboard.in/u:arthegall/b:c0f4c85f7ee5/ [1905.02383] Gaussian Differential Privacy 2019-05-09T11:31:42+00:00 https://arxiv.org/abs/1905.02383 arthegallaaron-roth differential-privacy via:arsyed composition machinelearning privacy https://pinboard.in/ https://pinboard.in/u:arthegall/b:25769862ca6e/ [1902.04114] Using Embeddings to Correct for Unobserved Confounding 2019-02-20T11:12:28+00:00 https://arxiv.org/abs/1902.04114 arthegall victor-veitch arxiv research-article machinelearning confounding causal-learning causality https://pinboard.in/ https://pinboard.in/u:arthegall/b:9ba4c0c69695/ [1902.06720] Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent 2019-02-20T11:07:36+00:00 https://arxiv.org/abs/1902.06720 arthegallvia:cshalizi neural-networks deep-learning arxiv research-article machinelearning gradient-descent https://pinboard.in/ https://pinboard.in/u:arthegall/b:3311b38c89da/ Blum, Hartline, "Near-optimal online auctions" (2005) 2018-09-23T10:49:41+00:00 https://dl.acm.org/citation.cfm?doid=1070597 arthegallauctions machinelearning randomization research-article online-algorithms https://pinboard.in/ https://pinboard.in/u:arthegall/b:d1b60c0a473d/ Weighted Sums of Random Kitchen Sinks: Replacing minimization with randomization in learning 2018-09-20T09:58:04+00:00 https://papers.nips.cc/paper/3495-weighted-sums-of-random-kitchen-sinks-replacing-minimization-with-randomization-in-learning arthegallmachinelearning via:cshalizi neural-networks randomization research-article nips https://pinboard.in/ https://pinboard.in/u:arthegall/b:0abe4325f74d/ [1806.07366] Neural Ordinary Differential Equations 2018-08-12T09:10:47+00:00 https://arxiv.org/abs/1806.07366 arthegallarxiv research-article machinelearning neural-networks differential-equations https://pinboard.in/ https://pinboard.in/u:arthegall/b:a00a40b1abd4/ [1807.10875] TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing 2018-08-12T09:10:19+00:00 https://arxiv.org/abs/1807.10875 arthegallneural-networks debugging machinelearning arxiv research-article ian-goodfellow testing https://pinboard.in/ https://pinboard.in/u:arthegall/b:1fba00836a86/ [1207.5910] Groups acting on Gaussian graphical models 2018-04-20T15:17:28+00:00 https://arxiv.org/abs/1207.5910 arthegall jan-draisma arxiv research-article graphical-models algebraic-statistics machinelearning https://pinboard.in/ https://pinboard.in/u:arthegall/b:618829dc4129/ [1610.09555] TensorLy: Tensor Learning in Python 2017-04-12T10:44:54+00:00 https://arxiv.org/abs/1610.09555 arthegall tensors arxiv machinelearning python https://pinboard.in/ https://pinboard.in/u:arthegall/b:d62648979419/ [1406.1837] A Credit Assignment Compiler for Joint Prediction 2017-04-12T10:44:03+00:00 https://arxiv.org/abs/1406.1837 arthegall learning-to-search machinelearning arxiv research-article compiler probabilistic-methods https://pinboard.in/ https://pinboard.in/u:arthegall/b:98311fa8e23d/ [1701.03757] Deep Probabilistic Programming 2017-03-08T04:40:41+00:00 https://arxiv.org/abs/1701.03757 arthegalldavid-blei probabilistic-programming deep-learning machinelearning arxiv preprint https://pinboard.in/ https://pinboard.in/u:arthegall/b:570bec91bc7b/ Tensor Decompositions for Learning Latent Variable Models 2017-03-08T04:17:58+00:00 http://jmlr.org/papers/v15/anandkumar14b.html arthegallmachinelearning research-article jmlr tensor-decomposition https://pinboard.in/ https://pinboard.in/u:arthegall/b:6b7a5811f4af/ [1611.00783] Preserving Randomness for Adaptive Algorithms 2016-11-30T18:55:30+00:00 https://arxiv.org/abs/1611.00783 arthegalladam-klivans arxiv preprint research-article adaptive-algorithms machinelearning https://pinboard.in/ https://pinboard.in/u:arthegall/b:b3e95478d0ed/ [1412.6980] Adam: A Method for Stochastic Optimization 2016-11-30T18:54:33+00:00 https://arxiv.org/abs/1412.6980 arthegalljimmy-ba arxiv optimization learning machinelearning stochastic-optimization https://pinboard.in/ https://pinboard.in/u:arthegall/b:2ae115625242/ Minimizing regret in dynamic decision problems | SpringerLink 2016-11-12T13:23:39+00:00 http://link.springer.com/article/10.1007/s11238-015-9526-8 arthegallregret machinelearning dynamic-problems research-article joseph-halpern https://pinboard.in/ https://pinboard.in/u:arthegall/b:6a8d20d3487b/ LIME - Local Interpretable Model-Agnostic Explanations – Marco Tulio Ribeiro – 2016-11-12T13:16:18+00:00 https://homes.cs.washington.edu/~marcotcr/blog/lime/ arthegalllime machinelearning classification interpretation https://pinboard.in/ https://pinboard.in/u:arthegall/b:bfd32c63af3a/ marcotcr/lime: Lime: Explaining the predictions of any machine learning classifier 2016-11-12T13:16:04+00:00 https://github.com/marcotcr/lime/ arthegallcode lime classification machinelearning opensource https://pinboard.in/ https://pinboard.in/u:arthegall/b:b7bf7960e8ed/ Double or Nothing: Multiplicative Incentive Mechanisms for Crowdsourcing 2016-11-03T17:32:52+00:00 https://papers.nips.cc/paper/5677-double-or-nothing-multiplicative-incentive-mechanisms-for-crowdsourcing arthegall incentive-compatible-mechanism nips research-article machinelearning crowdsourcing incentives https://pinboard.in/ https://pinboard.in/u:arthegall/b:a8f3027e23ab/ Glorot, Bengio, "Understanding the difficulty of training deep feedforward neural networks" JMLR (2010) 2016-11-03T17:24:16+00:00 http://jmlr.org/proceedings/papers/v9/glorot10a/glorot10a.pdf arthegalldeep-learning training research-article machinelearning jmlr https://pinboard.in/ https://pinboard.in/u:arthegall/b:4b258a89aa9e/ Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data 2016-11-03T17:20:42+00:00 https://arxiv.org/abs/1610.05755 arthegallarxiv deep-learning machinelearning differential-privacy research-article training-data anonymization https://pinboard.in/ https://pinboard.in/u:arthegall/b:c4c48a5adbbb/ [1609.07236] On the (im)possibility of fairness 2016-11-01T12:27:02+00:00 https://arxiv.org/abs/1609.07236 arthegallalgorithms ethics arxiv machinelearning research-article https://pinboard.in/ https://pinboard.in/u:arthegall/b:44e26f8a30de/ Dougal Sutherland, "Scalable, Flexible, and Active Learning on Distributions" 2016-10-27T16:52:34+00:00 https://www.cs.cmu.edu/~dsutherl/thesis.pdf arthegall active-learning machinelearning thesis distributions probabilistic-methods https://pinboard.in/ https://pinboard.in/u:arthegall/b:bca2c70a25b4/ Smile - Statistical Machine Intelligence and Learning Engine 2016-09-26T14:38:31+00:00 http://haifengl.github.io/smile/index.html arthegallsmile java machinelearning opensource software scala https://pinboard.in/ https://pinboard.in/u:arthegall/b:a6144436f347/ [1304.1467] Dimension Independent Matrix Square using MapReduce 2016-09-26T13:59:33+00:00 http://arxiv.org/abs/1304.1467 arthegall distributed-computing arxiv research-article similarity machinelearning gunnar-carlsson https://pinboard.in/ https://pinboard.in/u:arthegall/b:619feaeb732b/ Cortes et al. "Learning with Rejection" 2016-09-26T10:06:57+00:00 http://www.cs.nyu.edu/~mohri/pub/rej.pdf arthegallmachinelearning learning-theory research-article do-no-map work https://pinboard.in/ https://pinboard.in/u:arthegall/b:bc1b6b2db86a/ Secure Multi-party Differential Privacy 2016-09-23T15:30:53+00:00 https://papers.nips.cc/paper/6004-secure-multi-party-differential-privacy arthegallnips research-article differential-privacy machinelearning multi-party-computation https://pinboard.in/ https://pinboard.in/u:arthegall/b:d2b449683f21/ Discussion of "Fast Approximate Inference for Arbitrarily Large Semiparametric Regression Models via Message Passing" | Dustin Tran 2016-09-20T14:46:35+00:00 http://dustintran.com/blog/discussion-of-fast-approximate-inference arthegallregression variational-inference expectation-propagation discussion machinelearning andrew-gelman https://pinboard.in/ https://pinboard.in/u:arthegall/b:99be2bc15514/ [1412.4869] Expectation propagation as a way of life 2016-09-20T14:39:40+00:00 http://arxiv.org/abs/1412.4869 arthegall arxiv machinelearning approximation big-data research-article message-passing expectation-propagation https://pinboard.in/ https://pinboard.in/u:arthegall/b:1dcd87d9d0f1/ CSE522: Learning Theory 2016-09-16T18:18:12+00:00 http://courses.cs.washington.edu/courses/cse599s/14sp/scribes.html arthegall online-learning online-algorithms machinelearning class notes https://pinboard.in/ https://pinboard.in/u:arthegall/b:b7d9484ac0ea/ [1609.04120] Private Topic Modeling 2016-09-15T11:32:48+00:00 http://arxiv.org/abs/1609.04120 arthegalllda dirichlet-allocation differential-privacy topic-modeling machinelearning arxiv research-article https://pinboard.in/ https://pinboard.in/u:arthegall/b:73f22e312cac/ [1607.00710] Automatic Generation of Probabilistic Programming from Time Series Data 2016-08-26T18:06:16+00:00 http://arxiv.org/abs/1607.00710 arthegall probabilistic-programming arxiv machinelearning time-series https://pinboard.in/ https://pinboard.in/u:arthegall/b:031165b901de/ "Automatic Variational Inference in Stan" (NIPS 2016) 2016-08-26T02:41:36+00:00 https://papers.nips.cc/paper/5758-automatic-variational-inference-in-stan.pdf arthegallnips machinelearning stan mcmc automatic-differentiation andrew-gelman variational-methods https://pinboard.in/ https://pinboard.in/u:arthegall/b:f6ff5eda5be7/ [1607.08456] Kernel functions based on triplet similarity comparisons 2016-08-25T16:06:57+00:00 http://arxiv.org/abs/1607.08456 arthegallsimilarity embedding kernel-methods research-article machinelearning arxiv https://pinboard.in/ https://pinboard.in/u:arthegall/b:5213e507a672/ [1605.06197] Deep Generative Models with Stick-Breaking Priors 2016-08-25T02:06:53+00:00 http://arxiv.org/abs/1605.06197# arthegallstick-breaking dirichlet-process machinelearning research-article arxiv deep-learning https://pinboard.in/ https://pinboard.in/u:arthegall/b:6e4cc73094b7/ [1607.08845] Limit theorems for the Zig-Zag process 2016-08-25T02:05:36+00:00 http://arxiv.org/abs/1607.08845 arthegallsampling mcmc machinelearning research-article arxiv zig-zag https://pinboard.in/ https://pinboard.in/u:arthegall/b:53f0caab8992/ [1608.06879] AIDE: Fast and Communication Efficient Distributed Optimization 2016-08-25T02:05:11+00:00 http://arxiv.org/abs/1608.06879 arthegalldistributed-computing optimization alex-smola machinelearning research-article arxiv https://pinboard.in/ https://pinboard.in/u:arthegall/b:8aff65a0407e/ Rafael Frongillo, Ian Kash, "On Elicitation Complexity" 2016-08-09T11:03:24+00:00 https://papers.nips.cc/paper/5832-on-elicitation-complexity arthegall rafael-frongillo research-article nips machinelearning https://pinboard.in/ https://pinboard.in/u:arthegall/b:c58004c3fcde/ "A Statistical View of Machine Learning" (Shakir Mohamed) 2016-08-09T10:27:10+00:00 http://blog.shakirm.com/wp-content/uploads/2015/07/SVDL.pdf arthegall shakir-mohamed deep-learning machinelearning statistics notes via:twitter https://pinboard.in/ https://pinboard.in/u:arthegall/b:7fdfa0b662ad/ Voodoo Machine Learning for Clinical Predictions | bioRxiv 2016-06-28T03:51:57+00:00 http://biorxiv.org/content/early/2016/06/19/059774 arthegalloverfitting cross-validation machinelearning bioarxiv clinical-data https://pinboard.in/ https://pinboard.in/u:arthegall/b:63c196be6081/ [1601.07996] Feature Selection: A Data Perspective 2016-05-24T11:25:03+00:00 http://arxiv.org/abs/1601.07996 arthegallfeature-selection machinelearning arxiv research-article survey https://pinboard.in/ https://pinboard.in/u:arthegall/b:cbaa1c8514cc/ The Population Posterior and Bayesian Modeling on Streams 2016-05-24T11:23:56+00:00 https://papers.nips.cc/paper/5793-the-population-posterior-and-bayesian-modeling-on-streams arthegallnips machinelearning conference-article bayesian-methods streams https://pinboard.in/ https://pinboard.in/u:arthegall/b:8330a462f5a3/ [1310.0740v4] Pseudo-Marginal Bayesian Inference for Gaussian Processes 2016-05-24T11:22:07+00:00 http://arxiv.org/abs/1310.0740v4 arthegallguassian-processes mark-girolami approximation arxiv research-article machinelearning https://pinboard.in/ https://pinboard.in/u:arthegall/b:59e924e98c79/