{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T10:10:00Z","timestamp":1756635000827,"version":"3.37.3"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DMS-1818945"],"award-info":[{"award-number":["DMS-1818945"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DMS-1820827"],"award-info":[{"award-number":["DMS-1820827"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01GM131642"],"award-info":[{"award-number":["R01GM131642"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000879","name":"Alfred P. Sloan Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000879","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DMS-2012266"],"award-info":[{"award-number":["DMS-2012266"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100001832","name":"Russel Sage Foundation","doi-asserted-by":"publisher","award":["2196"],"award-info":[{"award-number":["2196"]}],"id":[{"id":"10.13039\/100001832","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Intel Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1109\/tit.2022.3175691","type":"journal-article","created":{"date-parts":[[2022,5,17]],"date-time":"2022-05-17T19:48:49Z","timestamp":1652816929000},"page":"6631-6662","source":"Crossref","is-referenced-by-count":6,"title":["Classification Logit Two-Sample Testing by Neural Networks for Differentiating Near Manifold Densities"],"prefix":"10.1109","volume":"68","author":[{"given":"Xiuyuan","family":"Cheng","sequence":"first","affiliation":[{"name":"Department of Mathematics, Duke University, Durham, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1423-9624","authenticated-orcid":false,"given":"Alexander","family":"Cloninger","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Halicioğlu Data Science Institute, University of California at San Diego, San Diego, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-1923-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl242"},{"key":"ref3","first-page":"1981","article-title":"Fast two-sample testing with analytic representations of probability measures","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chwialkowski"},{"key":"ref4","first-page":"181","article-title":"Interpretable distribution features with maximum testing power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jitkrittum"},{"key":"ref5","first-page":"1","article-title":"Revisiting classifier two-sample tests","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lopez-Paz"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaz018"},{"key":"ref7","first-page":"1718","article-title":"Generative moment matching networks","volume-title":"Proc. ICML","author":"Li"},{"key":"ref8","first-page":"2203","article-title":"MMD GAN: Towards deeper understanding of moment matching network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3156\/jsoft.29.5_177_2"},{"key":"ref10","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref11","first-page":"271","article-title":"F-GAN: Training generative neural samplers using variational divergence minimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nowozin"},{"key":"ref12","first-page":"829","article-title":"Statistical model criticism using kernel two sample tests","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lloyd"},{"key":"ref13","first-page":"1","article-title":"Generative models and model criticism via optimized maximum mean discrepancy","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Sutherland"},{"key":"ref14","first-page":"2606","article-title":"A kernel test of goodness of fit","volume-title":"Proc. Workshop Conf.","author":"Chwialkowski"},{"key":"ref15","first-page":"276","article-title":"A kernelized stein discrepancy for goodness-of-fit tests","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref16","first-page":"262","article-title":"A linear-time kernel goodness-of-fit test","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jitkrittum"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1006\/jmva.1994.1033"},{"issue":"1","key":"ref18","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","article-title":"On integral probability metrics, \u03a6-divergences and binary classification","volume-title":"arXiv:0901.2698","author":"Sriperumbudur","year":"2009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s00180-015-0633-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00492"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2163380"},{"key":"ref23","article-title":"Deep ReLU network approximation of functions on a manifold","volume-title":"arXiv:1908.00695","author":"Schmidt-Hieber","year":"2019"},{"key":"ref24","article-title":"Statistical guarantees of generative adversarial networks for distribution estimation","volume-title":"arXiv:2002.03938","author":"Chen","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.07.002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/18M118709X"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-020-09461-0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2016.04.003"},{"key":"ref29","article-title":"Nonparametric regression on low-dimensional manifolds using deep ReLU networks: Function approximation and statistical recovery","volume-title":"arXiv:1908.01842","author":"Chen","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2017.08.007"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_22"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176348650"},{"volume-title":"An Introduction to Modern Nonparametric Statistics","year":"2004","author":"Higgins","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.2172\/826696"},{"issue":"3","key":"ref35","first-page":"731","article-title":"Information, divergence and risk for binary experiments","volume":"12","author":"Reid","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1214\/20-aos1962"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273507"},{"key":"ref38","first-page":"2137","article-title":"Discriminative learning under covariate shift","volume":"10","author":"Bickel","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref39","first-page":"304","article-title":"Linking losses for density ratio and class-probability estimation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Menon"},{"key":"ref40","article-title":"Learning in implicit generative models","volume-title":"arXiv:1610.03483","author":"Mohamed","year":"2016"},{"key":"ref41","first-page":"1205","article-title":"Optimal kernel choice for large-scale two-sample tests","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gretton"},{"key":"ref42","first-page":"6316","article-title":"Learning deep kernels for non-parametric two-sample tests","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.1.164"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.07.011"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1137\/18M1189336"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.OA-2020-0149"},{"key":"ref47","article-title":"Depth creates no bad local minima","volume-title":"arXiv:1702.08580","author":"Lu","year":"2017"},{"key":"ref48","first-page":"853","article-title":"Elimination of all bad local minima in deep learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Kawaguchi"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1806579115"},{"key":"ref50","first-page":"8139","article-title":"On exact computation with an infinitely wide neural net","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Arora"},{"key":"ref51","first-page":"322","article-title":"Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arora"},{"key":"ref52","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen-Zhu"},{"key":"ref53","first-page":"1675","article-title":"Gradient descent finds global minima of deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du"},{"key":"ref54","first-page":"6109","article-title":"Intrinsic dimension of data representations in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ansuini"},{"key":"ref55","first-page":"2294","article-title":"The manifold tangent classifier","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rifai"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1214\/19-EJS1551"},{"key":"ref57","first-page":"639","article-title":"Optimal approximation of continuous functions by very deep ReLU networks","volume-title":"Proc. Conf. Learn. Theory","author":"Yarotsky"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1002\/9780470316481"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05839-6"},{"key":"ref61","first-page":"10836","article-title":"Generalization bounds of stochastic gradient descent for wide and deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Cao"},{"key":"ref62","first-page":"1","article-title":"Neural tangent kernels, transportation mappings, and universal approximation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ji"},{"key":"ref63","first-page":"1","article-title":"Neural tangent kernel maximum mean discrepancy","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Cheng"},{"key":"ref64","first-page":"1","article-title":"On the linearity of large non-linear models: When and why the tangent kernel is constant","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88745-4"},{"key":"ref66","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref68","article-title":"ADADELTA: An adaptive learning rate method","volume-title":"arXiv:1212.5701","author":"Zeiler","year":"2012"},{"key":"ref69","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sutskever"},{"key":"ref70","first-page":"71","article-title":"Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shamir"},{"key":"ref71","first-page":"1","article-title":"Gradient descent provably optimizes over-parameterized neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Du"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/9893495\/9775969-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/9893495\/09775969.pdf?arnumber=9775969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T22:36:52Z","timestamp":1705963012000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9775969\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":71,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tit.2022.3175691","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"type":"print","value":"0018-9448"},{"type":"electronic","value":"1557-9654"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}