Minimax bounds for estimating multivariate Gaussian location mixtures
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, A.K.H. | - |
dc.contributor.author | Guntuboyina, A. | - |
dc.date.accessioned | 2022-05-03T08:42:10Z | - |
dc.date.available | 2022-05-03T08:42:10Z | - |
dc.date.created | 2022-05-03 | - |
dc.date.issued | 2022 | - |
dc.identifier.issn | 1935-7524 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/140677 | - |
dc.description.abstract | We prove minimax bounds for estimating Gaussian location mixtures on Rd under the squared L2 and the squared Hellinger loss functions. Under the squared L2 loss, we prove that the minimax optimal rate is upper and lower bounded by a constant multiple of n-1(log n)d/2. Under the squared Hellinger loss, we consider two subclasses based on the behavior of the tails of the mixing measure. When the mixing measure has a sub-Gaussian tail, the minimax rate under the squared Hellinger loss is bounded from below by (log n)d/n, which implies that the optimal minimax rate is between (log n)d/n and the upper bound (log n)d+1/n obtained by [11]. On the other hand, when the mixing measure is only assumed to have a bounded pth moment for a fixed p > 0, the minimax rate under the squared Hellinger loss is bounded from below by n−p/(p+d)(log n)-3d/2. This rate is minimax optimal up to logarithmic factors. © 2022, Institute of Mathematical Statistics. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | Institute of Mathematical Statistics | - |
dc.title | Minimax bounds for estimating multivariate Gaussian location mixtures | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, A.K.H. | - |
dc.identifier.doi | 10.1214/21-EJS1975 | - |
dc.identifier.scopusid | 2-s2.0-85128461961 | - |
dc.identifier.wosid | 000825293500026 | - |
dc.identifier.bibliographicCitation | Electronic Journal of Statistics, v.16, no.1, pp.1461 - 1484 | - |
dc.relation.isPartOf | Electronic Journal of Statistics | - |
dc.citation.title | Electronic Journal of Statistics | - |
dc.citation.volume | 16 | - |
dc.citation.number | 1 | - |
dc.citation.startPage | 1461 | - |
dc.citation.endPage | 1484 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Mathematics | - |
dc.relation.journalWebOfScienceCategory | Statistics & Probability | - |
dc.subject.keywordPlus | MAXIMUM-LIKELIHOOD | - |
dc.subject.keywordPlus | BAYES ESTIMATION | - |
dc.subject.keywordPlus | CONVERGENCE | - |
dc.subject.keywordPlus | RATES | - |
dc.subject.keywordAuthor | Almost parametric rate of convergence | - |
dc.subject.keywordAuthor | Assouad’s lemma | - |
dc.subject.keywordAuthor | Curse of dimensionality | - |
dc.subject.keywordAuthor | Minimax lower bounds | - |
dc.subject.keywordAuthor | Multivariate normal location mixtures | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.