Fast convergence of the expectation-maximization algorithm under a logarithmic Sobolev inequality

DOI10.1093/BIOMET/ASAF061MaRDI QIDQ6871645zbMATH OpenFDO

Authors Rocco Caprio, Adam M. Johansen

Publication date 20 January 2026

Published in Biometrika (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1093/BIOMET/ASAF061

zbMATH Keywords

empirical Bayes frameworkexpectation-maximization algorithmfirst-order EM algorithmfunctional inequalitylatent variable modellog-Sobolev inequalitymaximum likelihood estimatornon-asymptotic boundWasserstein gradient

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• Analysis and geometry of Markov diffusion operators
• Comparison of Markov chains via weak Poincaré inequalities with application to pseudo-marginal MCMC
• Cyclic seesaw process for optimization and identification
• Degenerate Nonlinear Programming with a Quadratic Growth Condition
• Dimension-free log-Sobolev inequalities for mixture distributions
• Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation
• Entropy dissipation of Fokker-Planck equations on graphs
• Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalities
• Exponential convergence of Langevin distributions and their discrete approximations
• Functional inequalities for perturbed measures with applications to log-concave measures and to some Bayesian problems
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• scientific article; zbMATH DE number 3124366 (Why is no real title available?)
• scientific article; zbMATH DE number 3567782 (Why is no real title available?)
• scientific article; zbMATH DE number 1222290 (Why is no real title available?)
• scientific article; zbMATH DE number 739537 (Why is no real title available?)
• scientific article; zbMATH DE number 1086057 (Why is no real title available?)
• scientific article; zbMATH DE number 3802652 (Why is no real title available?)
• scientific article; zbMATH DE number 788229 (Why is no real title available?)
• scientific article; zbMATH DE number 3894218 (Why is no real title available?)
• Interacting particle Langevin algorithm for maximum marginal likelihood estimation
• Logarithmic Sobolev Inequalities
• Logarithmic Sobolev inequalities and stochastic Ising models
• Maximum Likelihood Variance Components Estimation for Binary Data
• On the convergence of alternating minimization for convex programming with applications to iteratively reweighted least squares and decomposition schemes
• On the convergence of block coordinate descent type methods
• On the convergence properties of the EM algorithm
• On the global and componentwise rates of convergence of the EM algorithm
• On the rate of convergence of alternating minimization for non-smooth non-strongly convex optimization in Banach spaces
• On the trend to equilibrium for some dissipative systems with slowly increasing a priori bounds.
• Probabilistic approach for granular media equations in the non-uniformly convex case
• Simultaneous Clustering and Estimation of Heterogeneous Graphical Models
• Singularity, misspecification and the convergence rate of EM
• Statistical guarantees for the EM algorithm: from population to sample-based analysis
• Transportation cost for Gaussian and other product measures
• Weak logarithmic Sobolev inequalities and entropic convergence
• Weak Poincaré inequalities and L^2-convergence rates of Markov semigroups

This page was built for publication: Fast convergence of the expectation-maximization algorithm under a logarithmic Sobolev inequality

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6871645)