Convergence rate of random scan coordinate ascent variational inference under log-concavity

DOI10.1137/24M1670627MaRDI QIDQ6658291

Hugo Lavenant, Giacomo Zanella

Publication date: 8 January 2025

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

zbMATH Keywords

convex optimizationmean-field approximationBayesian computationoptimal transportiteration complexityblock-coordinate ascent

Mathematics Subject Classification ID

Convex programming (90C25) Distribution theory (60Exx) Optimal transportation (49Q22)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• On the complexity analysis of randomized block-coordinate descent methods
• An introduction to variational methods for graphical models
• Coordinate descent algorithms
• Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
• Efficiency of coordinate descent methods on huge-scale optimization problems
• Graphical Models, Exponential Families, and Variational Inference
• On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization
• One-dimensional empirical measures, order statistics, and Kantorovich transport distances
• Optimal Transport

This page was built for publication: Convergence rate of random scan coordinate ascent variational inference under log-concavity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6658291)