Fast incremental expectation maximization for finite-sum optimization: nonasymptotic convergence

DOI10.1007/s11222-021-10023-9zbMath1475.62032arXiv2012.14670OpenAlexW3115503773MaRDI QIDQ2058782

Gersende Fort, P. Gach, Eric Moulines

Publication date: 9 December 2021

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2012.14670

zbMATH Keywords

large scale learningcomputational statistical learningfinite-sum optimizationincremental expectation maximization algorithmmomentum stochastic approximation

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Numerical optimization and variational techniques (65K10) Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Stochastic variable metric proximal gradient with variance reduction for non-convex composite optimization

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Minimizing finite sums with the stochastic average gradient
• On the convergence properties of the EM algorithm
• Convergence of the Monte Carlo expectation maximization for curved exponential families.
• Convergence of a stochastic approximation version of the EM algorithm
• Mini-batch learning of exponential family finite mixture models
• Keeping the balance -- bridge sampling for marginal likelihood estimation in finite mixture, mixture of experts and Markov mixture models
• MM Optimization Algorithms
• On-Line Expectation–Maximization Algorithm for latent Data Models
• The EM Algorithm and Extensions, 2E
• Some NP-complete problems in quadratic and nonlinear programming
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Non-Linear Programming Via Penalty Functions
• Statistical Modelling by Exponential Families
• A Stochastic Approximation Method