Optimality Conditions for Nonsmooth Nonconvex-Nonconcave Min-Max Problems and Generative Adversarial Networks

DOI10.1137/22M1482238zbMath1522.90259arXiv2203.10914OpenAlexW4385721065MaRDI QIDQ6136233

No author found.

Publication date: 29 August 2023

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2203.10914

zbMATH Keywords

optimality conditionnonsmoothmin-max problemgenerative adversarial networksnonconvex-nonconcave

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) Stochastic programming (90C15) Complementarity and equilibrium problems and variational inequalities (finite dimensions) (aspects of mathematical programming) (90C33) Numerical methods for variational inequalities and related problems (65K15)

Related Items (3)

Data-driven distributionally robust multiproduct pricing problems under pure characteristics demand models ⋮ A quasi-Newton subspace trust region algorithm for nonmonotone variational inequalities in adversarial learning over box constraints ⋮ Distributionally robust variational inequalities: relaxation, quantification and discretization

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• On lower iteration complexity bounds for the convex concave saddle point problems
• A study of piecewise linear-quadratic programs
• Bilevel optimization. Advances and next challenges
• Pure characteristics demand models and distributionally robust mathematical programs with stochastic complementarity constraints
• A Generalized Second-Order Derivative in Nonsmooth Optimization
• Variational Analysis
• Convergence Analysis of Sample Average Approximation of Two-Stage Stochastic Generalized Equations
• Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
• On Gradient-Based Learning in Continuous Games
• Weakly-convex–concave min–max optimization: provable algorithms and applications in machine learning
• Exact Penalization of Generalized Nash Equilibrium Problems
• Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications
• Optimal Primal-Dual Methods for a Class of Saddle Point Problems
• Generalized Nash equilibrium problems

This page was built for publication: Optimality Conditions for Nonsmooth Nonconvex-Nonconcave Min-Max Problems and Generative Adversarial Networks