Weakly-convex–concave min–max optimization: provable algorithms and applications in machine learning

DOI10.1080/10556788.2021.1895152zbMath1502.90194arXiv1810.02060OpenAlexW3134825596MaRDI QIDQ5043854

Tianbao Yang, Ming-rui Liu, Qihang Lin, Hassan Rafique

Publication date: 6 October 2022

Published in: Optimization Methods and Software (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1810.02060

zbMATH Keywords

stochastic optimizationmin-max optimizationnon-convex optimizationnon-smooth optimization

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) Nonconvex programming, global optimization (90C26) Stochastic programming (90C15)

Related Items (12)

Zeroth-order single-loop algorithms for nonconvex-linear minimax problems ⋮ Zeroth-order algorithms for nonconvex-strongly-concave minimax problems with improved complexities ⋮ Adaptively weighted difference model of anisotropic and isotropic total variation for image denoising ⋮ The landscape of the proximal point method for nonconvex-nonconcave minimax optimization ⋮ A unified single-loop alternating gradient projection algorithm for nonconvex-concave and convex-nonconcave minimax problems ⋮ Decentralized Gradient Descent Maximization Method for Composite Nonconvex Strongly-Concave Minimax Problems ⋮ Optimality Conditions for Nonsmooth Nonconvex-Nonconcave Min-Max Problems and Generative Adversarial Networks ⋮ On Proximal Algorithms with Inertial Effects Beyond Monotonicity ⋮ Conservative parametric optimality and the ridge method for tame min-max problems ⋮ Alternating Proximal-Gradient Steps for (Stochastic) Nonconvex-Concave Minimax Problems ⋮ Unnamed Item ⋮ An Accelerated Inexact Proximal Point Method for Solving Nonconvex-Concave Min-Max Problems

Cites Work

• Unnamed Item
• Accelerated gradient methods for nonconvex nonlinear and stochastic programming
• Statistical consistency and asymptotic normality for high-dimensional robust \(M\)-estimators
• Efficiency of minimizing compositions of convex functions and smooth maps
• Robust Stochastic Approximation Approach to Stochastic Programming
• Monotone Operators and the Proximal Point Algorithm
• Stochastic Model-Based Minimization of Weakly Convex Functions
• Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications
• Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems
• Variance-based regularization with convex objectives
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming

This page was built for publication: Weakly-convex–concave min–max optimization: provable algorithms and applications in machine learning