Pinboard (mraginsky) https://pinboard.in/u:mraginsky/public/ recent bookmarks from mraginsky [2106.10717] Optimal potentials for hedging algorithms 2022-10-25T12:12:07+00:00 https://arxiv.org/abs/2106.10717 mraginsky papers to-read heard-the-talk online-learning game-theory SDEs https://pinboard.in/ https://pinboard.in/u:mraginsky/b:1f55d0ab96d4/ Tight Lower Bounds for the Multiplicative Weights Algorithm on the Experts Problem 2016-04-10T18:39:52+00:00 http://pages.cs.wisc.edu/~balu2901/papers/2016/experts_project.pdf mraginskypapers to-read machine-learning online-learning lower-bounds https://pinboard.in/ https://pinboard.in/u:mraginsky/b:7418040f07ea/ [1307.5449] Non-stationary Stochastic Optimization 2015-01-27T23:12:37+00:00 http://arxiv.org/abs/1307.5449 mraginsky papers to-read optimization online-learning decision-theory https://pinboard.in/ https://pinboard.in/u:mraginsky/b:a98c836f4524/ [1501.06225] Online Optimization : Competing with Dynamic Comparators 2015-01-27T20:41:30+00:00 http://arxiv.org/abs/1501.06225 mraginsky papers to-read online-learning decision-making https://pinboard.in/ https://pinboard.in/u:mraginsky/b:cade0b9c1de1/ [1405.6076] Online Linear Optimization via Smoothing 2014-05-31T15:25:24+00:00 http://arxiv.org/abs/1405.6076 mraginsky papers to-read online-learning optimization https://pinboard.in/ https://pinboard.in/u:mraginsky/b:833d4e441e54/ [1401.6956] A continuous-time approach to online optimization 2014-02-01T05:41:51+00:00 http://arxiv.org/abs/1401.6956 mraginsky papers to-read online-learning optimization https://pinboard.in/ https://pinboard.in/u:mraginsky/b:e9cf2e4966b8/ [1310.2997] Bandits with Switching Costs: T^{2/3} Regret 2013-10-14T01:33:29+00:00 http://arxiv.org/abs/1310.2997 mraginskypapers to-read bandit-problems online-learning https://pinboard.in/ https://pinboard.in/u:mraginsky/b:1ff3ed96dcfd/ [1207.1965] Forecasting electricity consumption by aggregating specialized experts 2012-07-10T19:51:15+00:00 http://arxiv.org/abs/1207.1965 mraginskypapers to-read online-learning prediction electricity-markets via:cshalizi https://pinboard.in/ https://pinboard.in/u:mraginsky/b:e5ccb37e41a3/ [1204.5721] Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems 2012-04-27T18:20:30+00:00 http://arxiv.org/abs/1204.5721 mraginsky papers to-read bandit-problems online-learning control-theory dynamic-programming decision-making https://pinboard.in/ https://pinboard.in/u:mraginsky/b:11d540786e36/ Why Generic Machine Learning Fails 2012-03-10T02:17:47+00:00 http://metamarkets.com/2011/machine-learning-in-wonderland/ mraginskyblogs machine-learning online-learning algorithms prediction computation https://pinboard.in/ https://pinboard.in/u:mraginsky/b:e27184963641/ "Online sequential optimization with biased gradients" 2012-02-21T15:48:40+00:00 http://www-bcf.usc.edu/~rusmevic/psfiles/biased-gradient.pdf mraginsky papers to-read online-learning optimization convex-programming https://pinboard.in/ https://pinboard.in/u:mraginsky/b:3fc1cff0c08b/ [1105.2274] Data-Distributed Weighted Majority and Online Mirror Descent 2012-02-21T03:26:47+00:00 http://arxiv.org/abs/1105.2274 mraginsky papers to-read machine-learning online-learning optimization distributed-systems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:2e2387fed77f/ [1102.2670] Online Least Squares Estimation with Self-Normalized Processes: An Application to Bandit Problems 2011-12-28T20:07:37+00:00 http://arxiv.org/abs/1102.2670 mraginskypapers to-read online-learning statistics bandit-problems https://pinboard.in/ https://pinboard.in/u:mraginsky/b:d154eceb3849/ Regret Bounds for the Adaptive Control of Linear Quadratic Systems (Abbasi-Yadkori and Szepesvari) 2011-12-28T19:57:23+00:00 http://www.ualberta.ca/~szepesva/papers/lqr_colt_final.pdf mraginskypapers to-read adaptive-systems control-theory online-learning https://pinboard.in/ https://pinboard.in/u:mraginsky/b:4c8b3a58144e/ Sebastien Bubeck, "Introduction to Online Optimization" 2011-12-22T04:02:24+00:00 http://www.princeton.edu/~sbubeck/BubeckLectureNotes.pdf mraginsky lecture-notes online-learning optimization prediction https://pinboard.in/ https://pinboard.in/u:mraginsky/b:a37ad4736dc0/ Adaptive Regret Minimization in Bounded-Memory Games 2011-11-16T17:11:01+00:00 http://arxiv.org/abs/1111.2888 mraginskypapers to-read online-learning game-theory bounded-rationality complexity via:shivak https://pinboard.in/u:mraginsky/b:e0615fbb18e4/ Internal Regret with Partial Monitoring: Calibration-Based Optimal Algorithms 2011-08-31T00:29:59+00:00 http://jmlr.csail.mit.edu/papers/v12/perchet11a.html mraginskypapers to-read online-learning decision-making optimization learning-theory game-theory https://pinboard.in/u:mraginsky/b:21b23bcabb20/ [1107.4080] On the Universality of Online Mirror Descent 2011-07-21T00:15:25+00:00 http://arxiv.org/abs/1107.4080 mraginskypapers to-read online-learning optimization learning-theory convex-programming https://pinboard.in/u:mraginsky/b:fa3bfc95da2c/ [1105.4701] Online Learning, Stability, and Stochastic Gradient Descent 2011-05-25T01:06:39+00:00 http://arxiv.org/abs/1105.4701 mraginsky papers online-learning optimization statistical-learning have-read https://pinboard.in/u:mraginsky/b:c8072df37b93/ Near-optimal no-regret algorithms for zero-sum games 2011-03-08T22:28:12+00:00 http://people.csail.mit.edu/costis/optimalNR.pdf mraginskypapers to-read online-learning game-theory decision-making optimization filetype:pdf media:document https://pinboard.in/u:mraginsky/b:76e2feea8b5d/ [1102.4442] Internal Regret with Partial Monitoring. Calibration-Based Optimal Algorithms 2011-02-23T02:56:29+00:00 http://arxiv.org/abs/1102.4442 mraginsky papers to-read learning-theory online-learning game-theory optimization https://pinboard.in/u:mraginsky/b:56261615f1b1/ [1102.0710] Universal Prior Prediction for Communication 2011-02-04T01:13:59+00:00 http://arxiv.org/abs/1102.0710 mraginsky papers to-read information-theory feedback-information-theory prediction online-learning https://pinboard.in/u:mraginsky/b:8e446b901115/ [1011.3168] Online Learning: Beyond Regret 2010-11-16T05:40:24+00:00 http://arxiv.org/abs/1011.3168 mraginskypapers to-read online-learning game-theory decision-making statistical-learning https://pinboard.in/u:mraginsky/b:1e209136787d/ [1011.1936] Blackwell Approachability and Low-Regret Learning are Equivalent 2010-11-10T01:29:58+00:00 http://arxiv.org/abs/1011.1936 mraginsky to-read papers online-learning decision-making game-theory optimization https://pinboard.in/u:mraginsky/b:51e700a8d185/ [1011.0686] No-Regret Reductions for Imitation Learning and Structured Prediction 2010-11-03T00:32:48+00:00 http://arxiv.org/abs/1011.0686 mraginskypapers to-read machine-learning online-learning prediction https://pinboard.in/u:mraginsky/b:a70a1ab73543/ [1008.4654] Freezing and Sleeping: Tracking Experts that Learn by Evolving Past Posteriors 2010-08-30T00:20:59+00:00 http://arxiv.org/abs/1008.4654 mraginsky papers to-read online-learning decision-making machine-learning algorithms https://pinboard.in/u:mraginsky/b:46c0e21d3026/ Dual Averaging Methods for Regularized Stochastic Learning and Online Optimization - Microsoft Research 2010-07-28T19:49:22+00:00 http://research.microsoft.com/apps/pubs/default.aspx?id=81322 mraginskypapers to-read optimization online-learning convex-programming https://pinboard.in/u:mraginsky/b:892d2ce9b8dd/ [1006.4039] Cooperative Autonomous Online Learning 2010-06-23T16:54:25+00:00 http://arxiv.org/abs/1006.4039 mraginsky papers have-read decision-making online-learning distributed-systems https://pinboard.in/u:mraginsky/b:5098c941c00f/ [1006.1138] Online Learning: Random Averages, Combinatorial Parameters, and Learnability 2010-06-08T00:30:54+00:00 http://arxiv.org/abs/1006.1138 mraginsky papers to-read learning-theory online-learning measure-concentration https://pinboard.in/u:mraginsky/b:898067021cf4/