DeepAI
Log In Sign Up

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

11/24/2020
by   Gersende Fort, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/30/2020

A Stochastic Path-Integrated Differential EstimatoR Expectation Maximization Algorithm

The Expectation Maximization (EM) algorithm is of key importance for inf...
11/03/2021

Federated Expectation Maximization with heterogeneity mitigation and variance reduction

The Expectation Maximization (EM) algorithm is the default algorithm for...
05/25/2021

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

Incremental Expectation Maximization (EM) algorithms were introduced to ...
12/29/2020

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

Fast Incremental Expectation Maximization (FIEM) is a version of the EM ...
06/06/2021

Stochastic EM methods with Variance Reduction for Penalised PET Reconstructions

Expectation-maximization (EM) is a popular and well-established method f...
05/25/2018

EM algorithms for ICA

Independent component analysis (ICA) is a widely spread data exploration...
03/15/2012

Anytime Planning for Decentralized POMDPs using Expectation Maximization

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