General procedure to provide high-probability guarantees for stochastic saddle point problems

DOI10.1007/S10915-024-02567-5MaRDI QIDQ6569676zbMATH OpenFDO

Authors Dongyang Li, Haobin Li, Junyu Zhang

Publication date 9 July 2024

Published in Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10915-024-02567-5

zbMATH Keywords

high-probability guaranteesample average approximationsample complexity boundstochastic saddle point problem

Mathematics Subject Classification ID

Stochastic programming (90C15) Complementarity and equilibrium problems and variational inequalities (finite dimensions) (aspects of mathematical programming) (90C33)

Recommendations

• scientific article; zbMATH DE number 7370566
• Gradient-Free Methods with Inexact Oracle for Convex-Concave Stochastic Saddle-Point Problem
• Accelerated stochastic algorithms for convex-concave saddle-point problems
• Confidence level solutions for stochastic programming

Cites work

• Accelerated schemes for a class of variational inequalities
• Accelerated stochastic algorithms for convex-concave saddle-point problems
• Extragradient Method with Variance Reduction for Stochastic Variational Inequalities
• Gradient-Free Methods with Inexact Oracle for Convex-Concave Stochastic Saddle-Point Problem
• scientific article; zbMATH DE number 5145289 (Why is no real title available?)
• scientific article; zbMATH DE number 3790208 (Why is no real title available?)
• scientific article; zbMATH DE number 7370566 (Why is no real title available?)
• Loss minimization and parameter estimation with heavy tails
• New first-order algorithms for stochastic variational inequalities
• Optimal primal-dual methods for a class of saddle point problems
• Robust Stochastic Approximation Approach to Stochastic Programming
• Sample average approximation methods for a class of stochastic variational inequality problems
• Smooth minimization of non-smooth functions
• Solving variational inequalities with stochastic mirror-prox algorithm
• Stochastic dual coordinate ascent methods for regularized loss minimization
• Stochastic primal-dual coordinate method for regularized empirical risk minimization
• Variance-based regularization with convex objectives

This page was built for publication: General procedure to provide high-probability guarantees for stochastic saddle point problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6569676)