A new class of stochastic EM algorithms. Escaping local maxima and handling intractable sampling

DOI10.1016/J.CSDA.2020.107159OpenAlexW3118823227MaRDI QIDQ830097FDOQ830097

Juliette Chevallier, Stéphanie Allassonnière

Publication date: 7 May 2021

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.csda.2020.107159

Recommendations

• A stochastic approximation type EM algorithm for the mixture problem
• Convergence of a stochastic approximation version of the EM algorithm
• Stochastic versions of the em algorithm: an experimental study in the mixture case
• Coupling a stochastic approximation version of EM with an MCMC procedure
• A stochastic approximation algorithm for maximum-likelihood estimation with incomplete data

zbMATH Keywords

stochastic approximationstochastic optimizationtheoretical convergencetempered distributionEM-like algorithm

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Graphical models, exponential families, and variational inference
• Statistical analysis of finite mixture distributions
• Title not available (Why is that?)
• Finite mixture models
• Optimization by Simulated Annealing
• On the convergence properties of the EM algorithm
• Independent component analysis, a new concept?
• Choosing starting values for the EM algorithm for getting the highest likelihood in multivariate Gaussian mixture models
• Inference in hidden Markov models.
• Simple and Globally Convergent Methods for Accelerating the Convergence of Any EM Algorithm
• Acceleration of Stochastic Approximation by Averaging
• Asymptotic Statistics
• A Stochastic Approximation Method
• Approximate Bayesian computational methods
• Title not available (Why is that?)
• Convergence of a stochastic approximation version of the EM algorithm
• Damped Anderson Acceleration With Restarts and Monotonicity Control for Accelerating EM and EM-like Algorithms
• Maximizing Generalized Linear Mixed Model Likelihoods With an Automated Monte Carlo EM Algorithm
• Title not available (Why is that?)
• Stability of Stochastic Approximation under Verifiable Conditions
• Coupling and Ergodicity of Adaptive Markov Chain Monte Carlo Algorithms
• Markov chains and stochastic stability
• A quasi-Newton acceleration for high-dimensional optimization algorithms
• Maximum likelihood estimation in nonlinear mixed effects models
• Rates of convergence of the Hastings and Metropolis algorithms
• Title not available (Why is that?)
• Statistical guarantees for the EM algorithm: from population to sample-based analysis
• Finite mixture models and model-based clustering
• An introduction to variational methods for graphical models
• Convergence of the Monte Carlo expectation maximization for curved exponential families.
• The geometry of exponential families
• Measuring the component overlapping in the Gaussian mixture model
• Coupling a stochastic approximation version of EM with an MCMC procedure
• Construction of Bayesian deformable models via a stochastic approximation algorithm: a convergence study
• Quasi-Monte Carlo sampling to improve the efficiency of Monte Carlo EM
• Extension of the SAEM algorithm to left-censored data in nonlinear mixed-effects model: Application to HIV dynamics model
• f-SAEM: a fast stochastic approximation of the EM algorithm for nonlinear mixed effects models
• Coupling stochastic EM and approximate Bayesian computation for parameter inference in state-space models
• A stochastic algorithm for probabilistic independent component analysis
• Efficient Gaussian Sampling for Solving Large-Scale Inverse Problems Using MCMC

Cited In (10)

• Coupling a stochastic approximation version of EM with an MCMC procedure
• A stochastic approximation type EM algorithm for the mixture problem
• On the curved exponential family in the Stochastic Approximation Expectation Maximization Algorithm
• Properties of the stochastic approximation EM algorithm with mini-batch sampling
• Global implicit function theorems and the online expectation–maximisation algorithm
• Randomized extrapolation for accelerating EM-type fixed-point algorithms
• Missing link survival analysis with applications to available pandemic data
• Reverse EM-problem based on Bregman divergence and its application to classical and quantum information theory
• Convergent stochastic expectation maximization algorithm with efficient sampling in high dimension. Application to deformable template model estimation
• Title not available (Why is that?)

Uses Software

• UCI-ml
• Monolix

This page was built for publication: A new class of stochastic EM algorithms. Escaping local maxima and handling intractable sampling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q830097)