{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T14:34:45Z","timestamp":1759674885261},"reference-count":33,"publisher":"MIT Press","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2016,1]]},"abstract":"<jats:p>We argue that when faced with big data sets, learning and inference algorithms should compute updates using only subsets of data items. We introduce algorithms that use sequential hypothesis tests to adaptively select such a subset of data points. The statistical properties of this subsampling process can be used to control the efficiency and accuracy of learning or inference. In the context of learning by optimization, we test for the probability that the update direction is no more than 90 degrees in the wrong direction. In the context of posterior inference using Markov chain Monte Carlo, we test for the probability that our decision to accept or reject a sample is wrong. We experimentally evaluate our algorithms on a number of models and data sets.<\/jats:p>","DOI":"10.1162\/neco_a_00796","type":"journal-article","created":{"date-parts":[[2015,12,22]],"date-time":"2015-12-22T20:22:06Z","timestamp":1450815726000},"page":"45-70","source":"Crossref","is-referenced-by-count":1,"title":["Sequential Tests for Large-Scale Learning"],"prefix":"10.1162","volume":"28","author":[{"given":"Anoop","family":"Korattikara","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of California, Irvine, Irvine, CA 92697, U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutian","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Engineering, University of Cambridge, Cambridge CB2 1PZ, U.K., and University of California, Irvine, Irvine, CA 92697, U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"Welling","sequence":"additional","affiliation":[{"name":"Informatics Institute, University of Amsterdam, 1098 XH Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"B1","author":"Ahn S.","year":"2012","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"B2","first-page":"1","volume":"25","author":"Alquier P.","year":"2014","journal-title":"Statistics and Computing"},{"key":"B3","first-page":"757","volume-title":"Advances in neural information processing systems","volume":"9","author":"Amari S.-I.","year":"1996"},{"key":"B4","author":"Bache K.","year":"2013","journal-title":"UCI machine learning repository"},{"key":"B5","first-page":"405","volume-title":"Proceedings of the 31st International Conference on Machine Learning","author":"Bardenet R.","year":"2014"},{"key":"B6","volume-title":"Proceedings of the 12th International Conference on Music Information Retrieval","author":"Bertin-Mahieux T.","year":"2011"},{"key":"B7","first-page":"2196","volume-title":"Advances in neural information processing systems, 27","author":"Boyles L.","year":"2011"},{"key":"B8","first-page":"1683","volume-title":"Proceedings of the 31st International Conference on Machine Learning","author":"Chen T.","year":"2014"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2011.02.014"},{"key":"B10","author":"Chen Y.","year":"2015","journal-title":"Sublinear-time approximate MCMC transitions for probabilistic programs"},{"key":"B11","first-page":"3203","volume":"2","author":"Ding N.","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"B12","first-page":"185","volume-title":"Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics","author":"DuBois C.","year":"2014"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-70873-7"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/82.4.711"},{"key":"B15","first-page":"1303","volume":"14","author":"Hoffman M. D.","year":"2013","journal-title":"Journal of Machine Learning Research"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00026-5"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.2307\/2340569"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.149"},{"key":"B19","author":"Korattikara A.","year":"2011","journal-title":"Multivariate hypothesis tests for statistical optimization thesis"},{"key":"B20","first-page":"128","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Korattikara A.","year":"2011"},{"key":"B21","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Korattikara A.","year":"2014"},{"key":"B22","doi-asserted-by":"crossref","first-page":"301","DOI":"10.7551\/mitpress\/7496.003.0015","volume-title":"Large scale kernel machines","author":"Loosli G.","year":"2007"},{"key":"B23","volume-title":"Generalized linear models","author":"McCullagh P.","year":"1999"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1063\/1.1699114"},{"key":"B25","author":"Ouyang Z.","year":"2008","journal-title":"Bayesian additive regression kernels"},{"key":"B26","first-page":"3102","volume-title":"Advances in neural information processing systems","author":"Patterson S.","year":"2013"},{"key":"B27","author":"Pillai N. S.","year":"2014","journal-title":"Ergodicity of approximate MCMC chains with applications to large data sets"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"B29","first-page":"626","volume-title":"Advances in neural information processing systems, 10","author":"Roweis S.","year":"1998"},{"key":"B30","first-page":"1104","volume-title":"Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning","author":"Singh S.","year":"2012"},{"key":"B31","volume-title":"A guide to modern econometrics","author":"Verbeek M.","year":"2000"},{"key":"B32","author":"Welling M.","year":"2014","journal-title":"Exploiting the statistics of learning and inference"},{"key":"B33","first-page":"681","volume-title":"Proceedings of the 28th International Conference on Machine Learning","author":"Welling M.","year":"2011"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/NECO_a_00796","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T07:52:55Z","timestamp":1692172375000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/28\/1\/45-70\/8131"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,1]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,1]]}},"alternative-id":["10.1162\/NECO_a_00796"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_00796","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,1]]}}}