Pinboard (cshalizi) https://pinboard.in/u:cshalizi/public/ recent bookmarks from cshalizi Foster : Prediction in the Worst Case 2016-04-16T13:14:27+00:00 http://projecteuclid.org/euclid.aos/1176348140 cshalizi to:NB individual_sequence_prediction low-regret_learning prediction ensemble_methods have_read foster.dean_p. statistics calibration https://pinboard.in/ https://pinboard.in/u:cshalizi/b:371d45a2bee5/ Regret bounded by gradual variation for online convex optimization - Machine Learning 2014-04-07T12:12:40+00:00 http://link.springer.com/article/10.1007/s10994-013-5418-8 cshalizi to_read learning_theory low-regret_learning individual_sequence_prediction optimization re:growing_ensemble_project in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:63c75a023a08/ [1307.5944] Online Optimization in Dynamic Environments 2013-07-24T12:19:05+00:00 http://arxiv.org/abs/1307.5944 cshalizi low-regret_learning non-stationarity time_series prediction individual_sequence_prediction heard_the_talk re:growing_ensemble_project have_read in_NB willett.rebecca_m. https://pinboard.in/ https://pinboard.in/u:cshalizi/b:cee6cdfb34f9/ [1304.3708] Advice-Efficient Prediction with Expert Advice 2013-04-23T18:11:18+00:00 http://arxiv.org/abs/1304.3708 cshalizi low-regret_learning individual_sequence_prediction re:growing_ensemble_project in_NB bartlett.peter_l. https://pinboard.in/ https://pinboard.in/u:cshalizi/b:f69f84a4e327/ [cs/0508127] On context-tree prediction of individual sequences 2013-04-13T22:10:47+00:00 http://arxiv.org/abs/cs/0508127 cshalizi to:NB information_theory prediction individual_sequence_prediction markov_models re:AoS_project variable-length_markov_models_aka_context_trees https://pinboard.in/ https://pinboard.in/u:cshalizi/b:54fe82cb3afa/ Sparsity Regret Bounds for Individual Sequences in Online Linear Regression 2013-04-08T01:52:53+00:00 http://jmlr.csail.mit.edu/papers/v14/gerchinovitz13a.html cshalizi low-regret_learning individual_sequence_prediction regression machine_learning sparsity in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:d7456f1f12b0/ [1301.0534] Follow the Leader If You Can, Hedge If You Must 2013-01-07T23:07:12+00:00 http://arxiv.org/abs/1301.0534 cshalizi to_read individual_sequence_prediction low-regret_learning learning_theory re:growing_ensemble_project grunwald.peter in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:46c837991e65/ TRACKING CLIMATE MODELS 2012-11-19T23:36:13+00:00 http://faculty.cs.gwu.edu/~cmontel/mssa11.pdf cshalizi re:growing_ensemble_project non-stationarity time_series climate_change statistics individual_sequence_prediction monteleoni.claire in_NB have_read https://pinboard.in/ https://pinboard.in/u:cshalizi/b:6c35cd76ad26/ [1207.1965] Forecasting electricity consumption by aggregating specialized experts 2012-07-10T10:31:56+00:00 http://arxiv.org/abs/1207.1965 cshalizi have_read individual_sequence_prediction online_learning mixture_models machine_learning prediction re:growing_ensemble_project in_NB to:blog https://pinboard.in/ https://pinboard.in/u:cshalizi/b:aeab63e18d74/ Statistics Without Probability (Individual Sequences) « Normal Deviate 2012-07-04T15:39:26+00:00 http://normaldeviate.wordpress.com/2012/07/04/statistics-without-probability-individual-sequences/ cshaliziindividual_sequence_prediction kith_and_kin wasserman.larry https://pinboard.in/ https://pinboard.in/u:cshalizi/b:99246af55a1e/ [1206.4604] Learning the Experts for Online Sequence Prediction 2012-06-23T13:45:07+00:00 http://arxiv.org/abs/1206.4604 cshalizi to_read re:growing_ensemble_project individual_sequence_prediction machine_learning time_series online_learning in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:8e7e455d30c4/ Log-optimal portfolio 2012-06-22T20:00:15+00:00 http://www.cs.bme.hu/~oti/portfolio/ cshalizi to:NB individual_sequence_prediction prediction machine_learning https://pinboard.in/ https://pinboard.in/u:cshalizi/b:577a909a059c/ Interior-Point Methods for Full-Information and Bandit Online Learning 2012-06-12T22:03:59+00:00 http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6191328 cshalizi to:NB individual_sequence_prediction optimization machine_learning rakhlin.sasha re:growing_ensemble_project bandit_problems https://pinboard.in/ https://pinboard.in/u:cshalizi/b:0f20090d6199/ Statistical Learning Theory and Sequential Prediction 2012-06-05T12:24:22+00:00 http://www-stat.wharton.upenn.edu/~rakhlin/courses/stat928/stat928_notes.pdf cshalizi to_read statistics machine_learning learning_theory optimization learning_in_games low-regret_learning individual_sequence_prediction regression classifiers empirical_processes ensemble_methods online_learning in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:92e251d24aeb/ [1204.5721] Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems 2012-04-26T03:12:16+00:00 http://arxiv.org/abs/1204.5721 cshalizi to:NB individual_sequence_prediction online_learning bandit_problems re:knightian_uncertainty low-regret_learning https://pinboard.in/ https://pinboard.in/u:cshalizi/b:631fe225f62c/ Online Learning and Online Convex Optimization 2012-03-30T14:24:09+00:00 http://www.nowpublishers.com/product.aspx?product=MAL&doi=2200000018 cshalizi online_learning individual_sequence_prediction optimization learning_theory machine_learning learning_in_games low-regret_learning in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:c9de70393195/ [1202.3323] A new look at shifting regret 2012-02-29T18:16:29+00:00 http://arxiv.org/abs/1202.3323 cshalizi online_learning to_read individual_sequence_prediction non-stationarity re:growing_ensemble_project in_NB low-regret_learning have_read https://pinboard.in/ https://pinboard.in/u:cshalizi/b:ade1de531f10/ [math/0701419] Strategies for prediction under imperfect monitoring 2012-02-21T04:13:36+00:00 http://arxiv.org/abs/math/0701419 cshalizi to:NB prediction individual_sequence_prediction learning_in_games re:growing_ensemble_project https://pinboard.in/ https://pinboard.in/u:cshalizi/b:8a46f026681f/ Introduction to Online Optimization (Bubeck) 2011-12-23T21:22:29+00:00 http://www.princeton.edu/~sbubeck/BubeckLectureNotes.pdf cshalizi online_learning regression individual_sequence_prediction optimization machine_learning learning_theory via:mraginsky to_read to_teach:statcomp re:freshman_seminar_on_optimization in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:5b8e6bad6c1d/ [1111.6337] Regret Bound by Variation for Online Convex Optimization 2011-12-01T14:04:08+00:00 http://arxiv.org/abs/1111.6337 cshalizi to_read re:growing_ensemble_project learning_theory individual_sequence_prediction in_NB bandit_problems https://pinboard.in/ https://pinboard.in/u:cshalizi/b:2dacf3479f48/ Improved Regret Guarantees for Online Smooth Convex Optimization with Bandit Feedback 2011-11-01T12:20:50+00:00 http://jmlr.csail.mit.edu/proceedings/papers/v15/saha11a.html cshalizi decision_theory learning_theory machine_learning bandit_problems individual_sequence_prediction in_NB tewari.ambuj low-regret_learning https://pinboard.in/ https://pinboard.in/u:cshalizi/b:3c23a4b198f1/ Adaptive Bandits: Towards the Best History-Dependent Strategy 2011-11-01T12:19:19+00:00 http://jmlr.csail.mit.edu/proceedings/papers/v15/odalric11a.html cshalizi to:NB decision_theory learning_theory machine_learning bandit_problems individual_sequence_prediction https://pinboard.in/ https://pinboard.in/u:cshalizi/b:1b31392c16b9/ [1110.2755] Efficient Tracking of Large Classes of Experts 2011-10-13T12:35:00+00:00 http://arxiv.org/abs/1110.2755 cshalizi0$, and only $O(log n)$ times larger than the optimal order for $gamma=0$ for all typical regret bound types we examined. For example, for predicting binary sequences with switching parameters, our method achieves the optimal $O(log n)$ regret rate with time complexity $O(n^{1+gamma}log n)$ for any $gammain (0,1)$."]]> to_read re:growing_ensemble_project learning_theory individual_sequence_prediction lugosi.gabor in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:80aeab90a23a/ [1110.2529] The Generalization Ability of Online Algorithms for Dependent Data 2011-10-13T12:33:26+00:00 http://arxiv.org/abs/1110.2529 cshalizi learning_theory individual_sequence_prediction ergodic_theory mixing re:growing_ensemble_project re:XV_for_mixing stability_of_learning concentration_of_measure have_read re:your_favorite_dsge_sucks in_NB https://pinboard.in/ https://pinboard.in/u:cshalizi/b:0891bd9c9846/ [1106.2436] From Bandits to Experts: On the Value of Side-Observations 2011-06-16T04:05:48+00:00 http://arxiv.org/abs/1106.2436 cshalizilearning_theory individual_sequence_prediction to_read bandit_problems in_NB https://pinboard.in/u:cshalizi/b:b448f550879f/ [1103.0949] Adapting to Non-stationarity with Growing Expert Ensembles 2011-03-07T01:28:00+00:00 http://arxiv.org/abs/1103.0949 cshaliziself-promotion individual_sequence_prediction non-stationarity re:growing_ensemble_project ensemble_methods time_series to_teach:data_over_space_and_time https://pinboard.in/u:cshalizi/b:f2d8cecf5a2c/ Online Learning in Case of Unbounded Losses Using Follow the Perturbed Leader Algorithm 2011-02-04T07:36:05+00:00 http://jmlr.csail.mit.edu/papers/v12/vyugin11a.html cshaliziindividual_sequence_prediction online_learning learning_theory re:growing_ensemble_project in_NB low-regret_learning https://pinboard.in/u:cshalizi/b:cd208d1b9202/ [1011.3168] Online Learning: Beyond Regret 2010-11-21T23:07:17+00:00 http://arxiv.org/abs/1011.3168 cshaliziindividual_sequence_prediction learning_theory calibration prediction have_read https://pinboard.in/u:cshalizi/b:96de5e39b805/ Divergence in everything: bounding the regret in online optimization « The Information Structuralist 2010-11-21T23:05:18+00:00 http://infostructuralist.wordpress.com/2010/11/05/divergence-in-everything-bounding-the-regret-in-online-optimization/ cshaliziinformation_theory individual_sequence_prediction online_learning raginsky.maxim have_read https://pinboard.in/u:cshalizi/b:d63f6e631541/ Extracting certainty from uncertainty: regret bounded by variation in costs 2010-07-21T15:19:22+00:00 http://www.springerlink.com/content/68386v04t03752n1/ cshalizi learning_theory individual_sequence_prediction ensemble_methods re:growing_ensemble_project have_read https://pinboard.in/u:cshalizi/b:fc1525f12ba1/ IEEE Xplore - On the generalization ability of on-line learning algorithms 2010-07-01T14:15:30+00:00 http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1327806 cshalizi learning_theory large_deviations online_learning individual_sequence_prediction via:djm1107 re:your_favorite_dsge_sucks re:XV_for_mixing ensemble_methods have_read low-regret_learning https://pinboard.in/u:cshalizi/b:45e79ffb4005/