{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T01:56:06Z","timestamp":1762998966978},"reference-count":56,"publisher":"MIT Press","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2013,3]]},"abstract":"<jats:p>The goal of sufficient dimension reduction in supervised learning is to find the low-dimensional subspace of input features that contains all of the information about the output values that the input features possess. In this letter, we propose a novel sufficient dimension-reduction method using a squared-loss variant of mutual information as a dependency measure. We apply a density-ratio estimator for approximating squared-loss mutual information that is formulated as a minimum contrast estimator on parametric or nonparametric models. Since cross-validation is available for choosing an appropriate model, our method does not require any prespecified structure on the underlying distributions. We elucidate the asymptotic bias of our estimator on parametric models and the asymptotic convergence rate on nonparametric models. The convergence analysis utilizes the uniform tail-bound of a U-process, and the convergence rate is characterized by the bracketing entropy of the model. We then develop a natural gradient algorithm on the Grassmann manifold for sufficient subspace search. The analytic formula of our estimator allows us to compute the gradient efficiently. Numerical experiments show that the proposed method compares favorably with existing dimension-reduction approaches on artificial and benchmark data sets.<\/jats:p>","DOI":"10.1162\/neco_a_00407","type":"journal-article","created":{"date-parts":[[2012,12,28]],"date-time":"2012-12-28T18:30:10Z","timestamp":1356719410000},"page":"725-758","source":"Crossref","is-referenced-by-count":42,"title":["Sufficient Dimension Reduction via Squared-Loss Mutual Information Estimation"],"prefix":"10.1162","volume":"25","author":[{"given":"Taiji","family":"Suzuki","sequence":"first","affiliation":[{"name":"Department of Mathematical Informatics, University of Tokyo, Bunkyo-ku, Tokyo 113-8656, Japan"}]},{"given":"Masashi","family":"Sugiyama","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tokyo Institute of Technology, Meguro-ku, Tokyo 152-8552, Japan"}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1974.1100705"},{"key":"B2","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1111\/j.2517-6161.1966.tb00626.x","volume":"28","author":"Ali S. M.","year":"1966","journal-title":"Journal of the Royal Statistical Society, Series B"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1950-0051437-7"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1007\/BF01199316"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.2307\/2288473"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1198\/016214501753208979"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022411301790"},{"key":"B10","volume-title":"Advances in Neural information processing systems","volume":"14","author":"Collins M.","year":"2002"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1998.10474090"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316931"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1080\/03610920008832598"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1198\/016214504000001501"},{"key":"B15","volume-title":"Elements of information theory","author":"Cover T. M.","year":"2006"},{"key":"B16","first-page":"229","volume":"2","author":"Csisz\u00e1r I.","year":"1967","journal-title":"Studia Scientiarum Mathematicarum Hungarica"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1109\/18.761290"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1997.10473676"},{"key":"B19","first-page":"1539","volume-title":"Advances in neural information processing systems, 24","author":"Eberts M.","year":"2011"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479895290954"},{"key":"B21","first-page":"73","volume":"5","author":"Fukumizu K.","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOS637"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1145\/959242.959248"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45167-9_11"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1996.10476931"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1007\/11564089_7"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177730196"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.2307\/2282952"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/28.3-4.321"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1162\/0899766054323026"},{"key":"B31","first-page":"291","volume-title":"Proceedings of the Nineteenth International Conference on Machine Learning","author":"Kashima H.","year":"2002"},{"key":"B32","volume-title":"Proceedings of the 20th International Conference on Machine Learning","author":"Kashima H.","year":"2003"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/S1631-073X(03)00215-2"},{"key":"B34","first-page":"315","volume-title":"Proceedings of the Nineteenth International Conference on Machine Learning","author":"Kondor R. I.","year":"2002"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.066138"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.2307\/2290563"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1992.10476258"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2000.10474231"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1162\/153244302760200687"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068870"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2991-7"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1198\/016214507000000527"},{"key":"B44","volume-title":"Learning with kernels","author":"Sch\u00f6lkopf B.","year":"2002"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273600"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1162\/153244302760185252"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1214\/009053606000001226"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-10-S1-S52"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1162\/153244303322753742"},{"key":"B51","volume-title":"Empirical processes in M-estimation","author":"van de Geer S.","year":"2000"},{"key":"B52","volume-title":"Asymptotic statistics","author":"van der Vaart A. W.","year":"2000"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2545-2"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970128"},{"key":"B55","first-page":"391","volume-title":"Multivariate analysis","author":"Wold H.","year":"1966"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1214\/009053607000000352"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000001285"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/NECO_a_00407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T02:30:26Z","timestamp":1714789826000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/25\/3\/725-758\/7860"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,3]]},"references-count":56,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,3]]}},"alternative-id":["10.1162\/NECO_a_00407"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_00407","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,3]]}}}