MultiLevel Composite Stochastic Optimization via Nested Variance Reduction

DOI10.1137/19M1285457MaRDI QIDQ4987278

Lin Xiao, Junyu Zhang

Publication date: 3 May 2021

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

Full work available at URL: https://arxiv.org/abs/1908.11468

zbMATH Keywords

variance reductionproximal gradient methodcomposite stochastic optimization

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30) Stochastic programming (90C15) Randomized algorithms (68W20)

Related Items (6)

On the Divergence of Decentralized Nonconvex Optimization ⋮ Stochastic Multilevel Composition Optimization Algorithms with Level-Independent Convergence Rates ⋮ Hybrid SGD algorithms to solve stochastic composite optimization problems with application in sparse portfolio selection problems ⋮ Stochastic composition optimization of functions without Lipschitz continuous gradient ⋮ Distributed stochastic compositional optimization problems over directed networks ⋮ Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization

Uses Software

• ProxSARAH
• Saga
• SpiderBoost

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Gradient methods for minimizing composite functions
• Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
• Lectures on convex optimization
• Erratum to ``Risk-averse dynamic programming for Markov decision processes
• Statistical estimation of composite risk functionals and risk optimization problems
• First-Order Methods in Optimization
• Multilevel Stochastic Gradient Methods for Nested Composition Optimization
• Accelerating Stochastic Composition Optimization
• Error Bounds, Quadratic Growth, and Linear Convergence of Proximal Methods
• A Single Timescale Stochastic Approximation Method for Nested Stochastic Optimization
• A Proximal Stochastic Gradient Method with Progressive Variance Reduction
• Regularized Iterative Stochastic Approximation Methods for Stochastic Variational Inequality Problems
• Optimal Distributed Online Prediction using Mini-Batches
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Convex Analysis
• Extragradient Method with Variance Reduction for Stochastic Variational Inequalities
• SpiderBoost

This page was built for publication: MultiLevel Composite Stochastic Optimization via Nested Variance Reduction