{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T18:25:34Z","timestamp":1768415134144,"version":"3.49.0"},"reference-count":15,"publisher":"MIT Press - Journals","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2011,4]]},"abstract":"<jats:p> We discuss the expectation propagation (EP) algorithm for approximate Bayesian inference using a factorizing posterior approximation. For neural network models, we use a central limit theorem argument to make EP tractable when the number of parameters is large. For two types of models, we show that EP can achieve optimal generalization performance when data are drawn from a simple distribution. <\/jats:p>","DOI":"10.1162\/neco_a_00104","type":"journal-article","created":{"date-parts":[[2011,1,11]],"date-time":"2011-01-11T21:32:16Z","timestamp":1294781536000},"page":"1047-1069","source":"Crossref","is-referenced-by-count":2,"title":["Expectation Propagation with Factorizing Distributions: A Gaussian Approximation and Performance Results for Simple Models"],"prefix":"10.1162","volume":"23","author":[{"given":"Fabiano","family":"Ribeiro","sequence":"first","affiliation":[{"name":"Instituto de F\u00edsica, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, 05508-090, Brazil; Faculdade de Filosofia, Ci\u00eancias e Letras de Ribeir\u00e3o Preto, Universidade de S\u00e3o Paulo, S\u00e3o Paulo, 05508-10, Brazil; and National Institute of Science and Technology in Complex Systems, 10587 Rio de Janeiro, Brazil"}]},{"given":"Manfred","family":"Opper","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Berlin, 10587 Berlin, Germany"}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139164542"},{"key":"B3","volume-title":"Advanced mean field method: Theory and practice","author":"Ghahramani Z.","year":"2000"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1088\/0305-4470\/25\/23\/020"},{"key":"B5","first-page":"1679","volume":"6","author":"Kuss M.","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1088\/0305-4470\/22\/12\/018"},{"key":"B7","volume-title":"Information, physics, and computation","author":"M\u00e9zard M.","year":"2008"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511569920.017"},{"key":"B11","first-page":"2177","volume":"6","author":"Opper M.","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1561\/2200000001"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.45.6056"},{"key":"B14","first-page":"379","volume-title":"Proceedings of the Newton Institute Workshop on On-Line Learning","author":"Solla S.","year":"1998"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.21236\/ADA629956"},{"key":"B16","volume-title":"Advances in neural information processing systems","volume":"12","author":"Weiss Y.","year":"1999"},{"key":"B17","first-page":"61","volume-title":"Theoretical aspects of neural computation","author":"Winther O.","year":"1998"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/NECO_a_00104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:38:38Z","timestamp":1615585118000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/23\/4\/1047-1069\/7641"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4]]},"references-count":15,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2011,4]]}},"alternative-id":["10.1162\/NECO_a_00104"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_00104","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,4]]}}}