Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization

by   Gersende Fort, et al.

The Expectation Maximization (EM) algorithm is a key reference for inference in latent variable models; unfortunately, its computational cost is prohibitive in the large scale learning setting. In this paper, we propose an extension of the Stochastic Path-Integrated Differential EstimatoR EM (SPIDER-EM) and derive complexity bounds for this novel algorithm, designed to solve smooth nonconvex finite-sum optimization problems. We show that it reaches the same state of the art complexity bounds as SPIDER-EM; and provide conditions for a linear rate of convergence. Numerical results support our findings.


page 1

page 2

page 3

page 4


A Stochastic Path-Integrated Differential EstimatoR Expectation Maximization Algorithm

The Expectation Maximization (EM) algorithm is of key importance for inf...

Federated Expectation Maximization with heterogeneity mitigation and variance reduction

The Expectation Maximization (EM) algorithm is the default algorithm for...

The Perturbed Prox-Preconditioned SPIDER algorithm for EM-based large scale learning

Incremental Expectation Maximization (EM) algorithms were introduced to ...

Fast Incremental Expectation Maximization for finite-sum optimization: nonasymptotic convergence

Fast Incremental Expectation Maximization (FIEM) is a version of the EM ...

Stochastic EM methods with Variance Reduction for Penalised PET Reconstructions

Expectation-maximization (EM) is a popular and well-established method f...

EM algorithms for ICA

Independent component analysis (ICA) is a widely spread data exploration...

Anytime Planning for Decentralized POMDPs using Expectation Maximization

Decentralized POMDPs provide an expressive framework for multi-agent seq...

Please sign up or login with your details

Forgot password? Click here to reset