Primal-Dual Stochastic Gradient Method for Convex Programs with Many Functional Constraints

DOI10.1137/18M1229869zbMath1445.90070arXiv1802.02724OpenAlexW3035804846MaRDI QIDQ5114401

Yang-yang Xu

Publication date: 22 June 2020

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

Full work available at URL: https://arxiv.org/abs/1802.02724

zbMATH Keywords

adaptive learningaugmented Lagrangian methoditeration complexityfunctional constraintstochastic gradient methodALMSGM

Mathematics Subject Classification ID

Analysis of algorithms (68W40) Convex programming (90C25) Large-scale problems in mathematical programming (90C06) Nonlinear programming (90C30) Stochastic programming (90C15)

Related Items (13)

A stochastic approximation method for convex programming with many semidefinite constraints ⋮ Adaptive primal-dual stochastic gradient method for expectation-constrained convex stochastic programs ⋮ A stochastic primal-dual method for a class of nonconvex constrained optimization ⋮ On the Convergence of Stochastic Primal-Dual Hybrid Gradient ⋮ First-Order Methods for Problems with $O$(1) Functional Constraints Can Have Almost the Same Convergence Rate as for Unconstrained Problems ⋮ An adaptive sampling augmented Lagrangian method for stochastic optimization with deterministic constraints ⋮ Stochastic inexact augmented Lagrangian method for nonconvex expectation constrained optimization ⋮ Randomized Lagrangian stochastic approximation for large-scale constrained stochastic Nash games ⋮ Primal-dual incremental gradient method for nonsmooth and convex optimization problems ⋮ New convergence analysis of a primal-dual algorithm with large stepsizes ⋮ A stochastic moving ball approximation method for smooth convex constrained minimization ⋮ Stochastic nested primal-dual method for nonconvex constrained composition optimization ⋮ An empirical quantile estimation approach for chance-constrained nonlinear optimization problems

Cites Work

• Unnamed Item
• Projection on the intersection of convex sets
• Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
• A sampling-and-discarding approach to chance-constrained optimization: feasibility and Optimality
• Subgradient methods for saddle-point problems
• Uncertain convex programs: randomized solutions and confidence levels
• Algorithms for stochastic optimization with function or expectation constraints
• Iteration complexity of inexact augmented Lagrangian methods for constrained convex programming
• Set intersection problems: supporting hyperplanes and quadratic programming
• The multiplier method of Hestenes and Powell applied to convex programming
• Stochastic First-Order Methods with Random Constraint Projection
• A Randomized Mirror-Prox Method for Solving Structured Large-Scale Matrix Saddle-Point Problems
• A Sample Approximation Approach for Optimization with Probabilistic Constraints
• Lectures on Stochastic Programming
• Robust Stochastic Approximation Approach to Stochastic Programming
• Augmented Lagrangians and Applications of the Proximal Point Algorithm in Convex Programming
• A Level-Set Method for Convex Optimization with a Feasible Solution Path
• A dual approach to solving nonlinear programming problems by unconstrained optimization
• Proximal-Proximal-Gradient Method
• Solving variational inequalities with Stochastic Mirror-Prox algorithm
• Optimal Primal-Dual Methods for a Class of Saddle Point Problems
• Neyman-Pearson classification, convexity and stochastic constraints
• Nonlinear Programming

This page was built for publication: Primal-Dual Stochastic Gradient Method for Convex Programs with Many Functional Constraints