{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T03:57:21Z","timestamp":1770695841233,"version":"3.49.0"},"reference-count":13,"publisher":"MIT Press - Journals","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2011,3]]},"abstract":"<jats:p> Optimization based on k-step contrastive divergence (CD) has become a common way to train restricted Boltzmann machines (RBMs). The k-step CD is a biased estimator of the log-likelihood gradient relying on Gibbs sampling. We derive a new upper bound for this bias. Its magnitude depends on k, the number of variables in the RBM, and the maximum change in energy that can be produced by changing a single variable. The last reflects the dependence on the absolute values of the RBM parameters. The magnitude of the bias is also affected by the distance in variation between the modeled distribution and the starting distribution of the Gibbs chain. <\/jats:p>","DOI":"10.1162\/neco_a_00085","type":"journal-article","created":{"date-parts":[[2010,12,16]],"date-time":"2010-12-16T18:36:06Z","timestamp":1292524566000},"page":"664-673","source":"Crossref","is-referenced-by-count":35,"title":["Bounding the Bias of Contrastive Divergence Learning"],"prefix":"10.1162","volume":"23","author":[{"given":"Asja","family":"Fischer","sequence":"first","affiliation":[{"name":"Institut f\u00fcr Neuroinformatik, Ruhr-Universit\u00e4t Bochum, 44780 Bochum, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Igel","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Copenhagen, 2100 Copenhagen \u00d8, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.11-07-647"},{"key":"B2","first-page":"153","volume-title":"Advances in neural information processing","volume":"19","author":"Bengio Y.","year":"2007"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3124-8"},{"key":"B4","first-page":"59","volume-title":"10th International Workshop on Artificial Intelligence and Statistics (AISTATS)","author":"Carreira-Perpi\u00f1\u00e1n M. \u00c1.","year":"2005"},{"key":"B5","first-page":"145","volume":"9","author":"Desjardins G.","year":"2010","journal-title":"Journal of Machine Learning Research Workshop and Conference Proceedings"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15825-4_26"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2007.09.004"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"B12","volume-title":"Failures of the one-step learning algorithm","author":"MacKay D.J.C.","year":"2001"},{"key":"B13","first-page":"194","volume-title":"Parallel distributed processing: Explorations in the microstructure of cognition, Vol. 1: Foundations","author":"Smolensky P.","year":"1986"},{"key":"B14","first-page":"1593","volume-title":"Advances in neural processing systems","volume":"17","author":"Yuille A. L.","year":"2005"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/NECO_a_00085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:38:32Z","timestamp":1615585112000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/23\/3\/664-673\/7646"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,3]]},"references-count":13,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2011,3]]}},"alternative-id":["10.1162\/NECO_a_00085"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_00085","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,3]]}}}