Stochastic (Approximate) Proximal Point Methods: Convergence, Optimality, and Adaptivity

DOI10.1137/18M1230323OpenAlexW2897048230WikidataQ127320778 ScholiaQ127320778MaRDI QIDQ5233106

John C. Duchi, Hilal Asi

Publication date: 16 September 2019

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

Full work available at URL: https://arxiv.org/abs/1810.05633

zbMATH Keywords

stochastic optimizationrobustnessadaptivityproximal methods

Mathematics Subject Classification ID

Large-scale problems in mathematical programming (90C06) Numerical optimization and variational techniques (65K10)

Related Items

Sub-linear convergence of a stochastic proximal iteration method in Hilbert space, Stochastic quasi-Newton with line-search regularisation, Hybrid SGD algorithms to solve stochastic composite optimization problems with application in sparse portfolio selection problems, A dual-based stochastic inexact algorithm for a class of stochastic nonsmooth convex composite problems, Adaptive step size rules for stochastic optimization in large-scale learning, Unnamed Item, Bellman filtering and smoothing for state-space models, On the computation of equilibria in monotone and potential stochastic hierarchical games, Unnamed Item, New nonasymptotic convergence rates of stochastic proximal point algorithm for stochastic convex optimization, Stochastic proximal splitting algorithm for composite minimization, Stochastic (Approximate) Proximal Point Methods: Convergence, Optimality, and Adaptivity, Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization

Uses Software

• Pegasos
• bmrm

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An optimal method for stochastic composite optimization
• Pegasos: primal estimated sub-gradient solver for SVM
• Incremental proximal methods for large scale convex optimization
• Local linear convergence for alternating and averaged nonconvex projections
• A randomized Kaczmarz algorithm with exponential convergence
• On approximate solutions of infinite systems of linear inequalities
• Introductory lectures on convex optimization. A basic course.
• Asymptotics in statistics. Some basic concepts.
• A Gauss-Newton method for convex composite optimization
• Asymptotic and finite-sample properties of estimators based on stochastic gradients
• Paved with good intentions: analysis of a randomized block Kaczmarz method
• Stochastic optimization problems with nondifferentiable cost functionals
• Asymptotic optimality in stochastic optimization
• Learning without Concentration
• Ergodic Convergence of a Stochastic Proximal Point Algorithm
• 10.1162/15324430260185628
• Randomized Methods for Linear Constraints: Convergence Rates and Conditioning
• The Cutting-Plane Method for Solving Convex Programs
• Lectures on Stochastic Programming
• Robust Stochastic Approximation Approach to Stochastic Programming
• Descent methods for composite nondifferentiable optimization problems
• Acceleration of Stochastic Approximation by Averaging
• Monotone Operators and the Proximal Point Algorithm
• Asymptotic Statistics
• Nonasymptotic convergence of stochastic proximal point algorithms for constrained convex optimization
• Stochastic Methods for Composite and Weakly Convex Optimization Problems
• Stochastic Model-Based Minimization of Weakly Convex Functions
• On Projection Algorithms for Solving Convex Feasibility Problems
• Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
• Error Bounds, Quadratic Growth, and Linear Convergence of Proximal Methods
• Stochastic (Approximate) Proximal Point Methods: Convergence, Optimality, and Adaptivity
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• A Stochastic Approximation Method
• The nonsmooth landscape of phase retrieval