English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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

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