Variance reduction techniques for stochastic proximal point algorithms

DOI10.1007/S10957-024-02502-6MaRDI QIDQ6644264FDOQ6644264

Authors: Cheik Traoré, Vassilis Apidopoulos, Saverio Salzo, Silvia Villa 

Publication date: 27 November 2024

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Recommendations

• A proximal stochastic gradient method with progressive variance reduction
• Variable metric proximal stochastic variance reduced gradient methods for nonconvex nonsmooth optimization
• Asymptotic estimates for \(r\)-Whitney numbers of the second kind
• Variance reduction for root-finding problems

zbMATH Keywords

stochastic optimizationproximal point algorithmvariance reduction techniquesSAGASVRG

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Convex programming (90C25)

Cites Work

• Adaptive subgradient methods for online learning and stochastic optimization
• A Stochastic Approximation Method
• Understanding machine learning. From theory to algorithms
• Title not available (Why is that?)
• The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
• Convex analysis and monotone operator theory in Hilbert spaces
• Incremental proximal methods for large scale convex optimization
• Stochastic (Approximate) Proximal Point Methods: Convergence, Optimality, and Adaptivity
• Some methods of speeding up the convergence of iteration methods
• Large-scale machine learning with stochastic gradient descent
• Minimizing finite sums with the stochastic average gradient
• From error bounds to the complexity of first-order descent methods for convex functions
• Error bounds, quadratic growth, and linear convergence of proximal methods
• Title not available (Why is that?)
• Nonasymptotic convergence of stochastic proximal point methods for constrained convex optimization
• Ergodic convergence of a stochastic proximal point algorithm
• Convergence rates for the heavy-ball continuous dynamics for non-convex optimization, under Polyak-Łojasiewicz condition
• On damped second-order gradient systems
• Asymptotic and finite-sample properties of estimators based on stochastic gradients
• Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry
• Linear convergence of prox-SVRG method for separable non-smooth convex optimization problems under bounded metric subregularity
• The Proximal Robbins–Monro Method
• A semismooth Newton stochastic proximal point algorithm with variance reduction

This page was built for publication: Variance reduction techniques for stochastic proximal point algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6644264)