Zeroth-order algorithms for nonconvex-strongly-concave minimax problems with improved complexities

DOI10.1007/s10898-022-01160-0zbMath1528.90280arXiv2001.07819OpenAlexW4225144511MaRDI QIDQ6064044

Meisam Razaviyayn, Krishnakumar Balasubramanian, Shi-Qian Ma, Zhongruo Wang

Publication date: 8 November 2023

Published in: Journal of Global Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2001.07819

zbMATH Keywords

minimax problemstochastic algorithmsoracle complexitygradient descent ascentzeroth-order algorithms

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Minimax problems in mathematical programming (90C47) Stochastic programming (90C15)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Bayesian optimization approach to find Nash equilibria
• Robust optimization with simulated annealing
• Lectures on convex optimization
• Introductory lectures on convex optimization. A basic course.
• Multi-agent reinforcement learning: a selective overview of theories and algorithms
• Derivative-free robust optimization by outer approximations
• Derivative-free optimization: a review of algorithms and comparison of software implementations
• Random gradient-free minimization of convex functions
• Zeroth-order nonconvex stochastic optimization: handling constraints, high dimensionality, and saddle points
• Introduction to Derivative-Free Optimization
• Derivative-Free and Blackbox Optimization
• Kernel-based methods for bandit convex optimization
• Weakly-convex–concave min–max optimization: provable algorithms and applications in machine learning
• Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming