{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:09:09Z","timestamp":1780510149504,"version":"3.54.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["EECS-1609279"],"award-info":[{"award-number":["EECS-1609279"]}]},{"name":"NSF","award":["CCF-1302435"],"award-info":[{"award-number":["CCF-1302435"]}]},{"name":"NSF","award":["CNS-1704778"],"award-info":[{"award-number":["CNS-1704778"]}]},{"name":"NSF","award":["CCF-1657420"],"award-info":[{"award-number":["CCF-1657420"]}]},{"name":"NSF","award":["CCF-1704828"],"award-info":[{"award-number":["CCF-1704828"]}]},{"name":"NSF","award":["CCF-2233152"],"award-info":[{"award-number":["CCF-2233152"]}]},{"name":"NSF Institute for Foundations of Machine Learning","award":["2019844"],"award-info":[{"award-number":["2019844"]}]},{"name":"research gifts by The University of Texas at Austin (UT Austin) Machine Learning (ML) Grant"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tit.2024.3435522","type":"journal-article","created":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T19:26:26Z","timestamp":1722281186000},"page":"6519-6546","source":"Crossref","is-referenced-by-count":3,"title":["Global Optimality of the EM Algorithm for Mixtures of Two-Component Linear Regressions"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7910-7817","authenticated-orcid":false,"given":"Jeongyeol","family":"Kwon","sequence":"first","affiliation":[{"name":"Wisconsin Institute for Discovery, University of Wisconsin–Madison, Madison, WI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4997-604X","authenticated-orcid":false,"given":"Wei","family":"Qian","sequence":"additional","affiliation":[{"name":"DiDi Research America, LLC, Fremont, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6416-5635","authenticated-orcid":false,"given":"Yudong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Sciences, University of Wisconsin–Madison, Madison, WI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Constantine","family":"Caramanis","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Damek","family":"Davis","sequence":"additional","affiliation":[{"name":"School of Operations Research and Information Engineering, Cornell University, Ithaca, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nhat","family":"Ho","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Sciences, The University of Texas at Austin, Austin, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1214\/16-AOS1435","article-title":"Statistical guarantees for the EM algorithm: From population to sample-based analysis","volume":"45","author":"Balakrishnan","year":"2017","journal-title":"The Ann. Statist."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646506"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/9781108644181"},{"key":"ref4","first-page":"648","article-title":"Reducibility and statistical-computational gaps from secret leakage","volume-title":"Proc. 33rd Conf. Learn. Theory","volume":"125","author":"Brennan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1214\/18-AOS1711"},{"key":"ref6","first-page":"1040","article-title":"Spectral experts for estimating mixtures of linear regressions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chaganty"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOS651"},{"key":"ref8","first-page":"560","article-title":"A convex formulation for mixed regression with two components: Minimax optimal rates","volume-title":"Proc. Conf. Learn. Theory","author":"Chen"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2017.2773474"},{"key":"ref10","first-page":"704","article-title":"Ten steps of EM suffice for mixtures of two Gaussians","volume-title":"Proc. Conf. Learn. Theory","author":"Daskalakis"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0167-9473(89)90043-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2307\/2984875"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/19-AOS1924"},{"key":"ref14","first-page":"4116","article-title":"Local maxima in the likelihood of Gaussian mixture models: Structural results and algorithmic consequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.181"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(95)00014-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2891628"},{"key":"ref18","first-page":"2425","article-title":"The EM algorithm gives sample-optimality for learning mixtures of well-separated Gaussians","volume-title":"Proc. Conf. Learn. Theory","author":"Kwon"},{"key":"ref19","first-page":"1727","article-title":"EM converges for a mixture of many linear regressions","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Kwon"},{"key":"ref20","first-page":"2055","article-title":"Global convergence of the EM algorithm for mixtures of two component linear regression","volume-title":"Proc. Conf. Learn. Theory","author":"Kwon"},{"key":"ref21","first-page":"1405","article-title":"On the minimax optimality of the EM algorithm for learning two-component mixed linear regression","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Kwon"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-20212-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asp011"},{"key":"ref24","first-page":"1125","article-title":"Learning mixtures of linear regressions with nearly optimal complexity","volume-title":"Proc. Conf. Learn. Theory","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300014764"},{"key":"ref26","first-page":"634","article-title":"On the analysis of EM for truncated mixtures of two Gaussians","volume-title":"Proc. 31st Int. Conf. Algorithmic Learning Theory","author":"Nagarajan"},{"key":"ref27","first-page":"4794","article-title":"Global convergence of least squares EM for demixing two log-concave densities","volume-title":"Proc. Neural Inf. Process. Syst. (NeurIPS)","author":"Qian"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1137\/1026034"},{"key":"ref29","first-page":"1223","article-title":"Provable tensor methods for learning mixtures of generalized linear models","volume-title":"Proc. Artif. Intell. Statist.","author":"Sedghi"},{"key":"ref30","volume-title":"High-Dimensional Probability: An Introduction With Applications in Data Science","author":"Vershynin","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/9781108627771"},{"key":"ref32","article-title":"High dimensional expectation-maximization algorithm: Statistical optimization and asymptotic normality","author":"Wang","year":"2014","journal-title":"arXiv:1412.8729"},{"issue":"103","key":"ref33","first-page":"1","article-title":"The EM algorithm is adaptively-optimal for unbalanced symmetric Gaussian mixtures","volume":"23","author":"Weinberger","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176346060"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.4171\/msl\/29"},{"key":"ref36","first-page":"2676","article-title":"Global analysis of expectation maximization for mixtures of two Gaussians","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.1.129"},{"key":"ref38","first-page":"6956","article-title":"Convergence of gradient EM on multi-component mixture of Gaussians","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yan"},{"key":"ref39","first-page":"1567","article-title":"Regularized EM algorithms: A unified framework and statistical guarantees","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yi"},{"key":"ref40","first-page":"613","article-title":"Alternating minimization for mixed linear regression","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yi"},{"key":"ref41","article-title":"Solving a mixture of many random linear equations by tensor decomposition and alternating minimization","author":"Yi","year":"2016","journal-title":"arXiv:1608.05749"},{"key":"ref42","first-page":"2190","article-title":"Mixed linear regression with multiple components","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhong"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/10642977\/10614292-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/18\/10642977\/10614292.pdf?arnumber=10614292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T04:06:27Z","timestamp":1725163587000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10614292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":42,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tit.2024.3435522","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}