Randomly initialized EM algorithm for two-component Gaussian mixture achieves near optimality in \(O(\sqrt{n})\) iterations

DOI10.4171/MSL/29zbMath1493.62350arXiv1908.10935MaRDI QIDQ2113265

Yanyan Li

Publication date: 11 March 2022

Published in: Mathematical Statistics and Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1908.10935

zbMATH Keywords

EM algorithmGaussian mixtureconvergence rateminimax ratesrandom initialization

Mathematics Subject Classification ID

Hypothesis testing in multivariate analysis (62H15) Minimax procedures in statistical decision theory (62C20)

Related Items (5)

Iterative algorithm for discrete structure recovery ⋮ Optimal estimation of high-dimensional Gaussian location mixtures ⋮ Sharp global convergence guarantees for iterative nonconvex optimization with random data ⋮ Optimal estimation and computational limit of low-rank Gaussian mixtures ⋮ Sharp optimal recovery in the two component Gaussian mixture model

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On the rate of convergence in Wasserstein distance of the empirical measure
• Convergence rates of parameter estimation for some weakly identifiable finite mixtures
• Statistical guarantees for the EM algorithm: from population to sample-based analysis
• Choosing starting values for the EM algorithm for getting the highest likelihood in multivariate Gaussian mixture models
• Choosing initial values for the EM algorithm for finite mixtures
• The transportation cost from the uniform measure to the empirical measure in dimension \(\geq 3\)
• Information-theoretic determination of minimax rates of convergence
• Rates of convergence for the Gaussian mixture sieve.
• Adaptive estimation of a quadratic functional by model selection.
• Entropies and rates of convergence for maximum likelihood and Bayes estimation for mixtures of normal densities.
• The landscape of empirical risk for nonconvex losses
• Singularity, misspecification and the convergence rate of EM
• On the nonparametric maximum likelihood estimator for Gaussian location mixture densities with application to Gaussian denoising
• Optimal estimation of Gaussian mixtures via denoised method of moments
• Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval
• Sparse PCA: optimal rates and adaptive estimation
• Dissipation of Information in Channels With Input Constraints
• Mixture Densities, Maximum Likelihood and the EM Algorithm
• Asymptotic Statistics
• Trust Region Methods
• Functional Properties of Minimum Mean-Square Error and Mutual Information

This page was built for publication: Randomly initialized EM algorithm for two-component Gaussian mixture achieves near optimality in \(O(\sqrt{n})\) iterations