Multidimensional two-component Gaussian mixtures detection

DOI10.1214/17-AIHP823MaRDI QIDQ1650120zbMATH OpenWikidataFDO

Authors Béatrice Laurent, Clément Marteau, Cathy Maugis-Rabusseau

Publication date 29 June 2018

Published in Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1509.09129, https://projecteuclid.org/euclid.aihp/1524643231

zbMATH Keywords

Gaussian mixturesseparation ratesnon-asymptotic testing procedure

Mathematics Subject Classification ID

Hypothesis testing in multivariate analysis (62H15) Order statistics; empirical distribution functions (62G30)

Abstract: Let $(X_1,ldots,X_n)$ be a $d$-dimensional i.i.d sample from a distribution with density $f$. The problem of detection of a two-component mixture is considered. Our aim is to decide whether $f$ is the density of a standard Gaussian random $d$-vector ($f=ph{i}_d$) against $f$ is a two-component mixture: $f=(1-varepsilon)ph{i}_d+varepsilonph{i}_d(.-mu)$ where $(varepsilon,mu)$ are unknown parameters. Optimal separation conditions on $varepsilon,mu,n$ and the dimension $d$ are established, allowing to separate both hypotheses with prescribed errors. Several testing procedures are proposed and two alternative subsets are considered.

Recommendations

• Non-asymptotic detection of two-component mixtures with unknown means
• scientific article; zbMATH DE number 887267
• Test on components of mixture densities
• Detection and feature selection in sparse mixture models
• Adaptive test on components of densities mixture

Cites work

• scientific article; zbMATH DE number 1052820 (Why is no real title available?)
• Adaptive estimation of a quadratic functional by model selection.
• An alternative point of view on Lepski's method
• Asymptotic distribution of the likelihood ratio test that a mixture of two binomials is a single binomial
• Detection and feature selection in sparse mixture models
• Detection of a sparse submatrix of a high-dimensional noisy matrix
• Detection of an anomalous cluster in a network
• Estimation and confidence sets for sparse normal mixtures
• Finite mixture models
• Higher criticism for detecting sparse heterogeneous mixtures.
• Minimax detection of a signal for \(l^ n\)-balls.
• Non asymptotic minimax rates of testing in signal detection with heterogeneous variances
• Non-asymptotic detection of two-component mixtures with unknown means
• Non-asymptotic minimax rates of testing in signal detection
• Nonparametric goodness-of-fit testing under Gaussian models
• Optimal Detection of Sparse Mixtures Against a Given Null Distribution
• Optimal detection of heterogeneous and heteroscedastic mixtures
• Optimal detection of sparse principal components in high dimension
• Recent asymptotic results in testing for mixtures
• The likelihood ratio test for general mixture models with or without structural parameter

Cited in

(8)

• Post-clustering difference testing: valid inference and practical considerations with applications to ecological and biological data
• Detection and feature selection in sparse mixture models
• Non-asymptotic detection of two-component mixtures with unknown means
• Optimal detection of heterogeneous and heteroscedastic mixtures
• Bounds in \(L^1\) Wasserstein distance on the normal approximation of general M-estimators
• Detecting anomalies in fibre systems using 3-dimensional image data
• scientific article; zbMATH DE number 2034560 (Why is no real title available?)
• A statistical test for mixture detection with application to component identification in multidimensional biomolecular NMR studies

This page was built for publication: Multidimensional two-component Gaussian mixtures detection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1650120)