First-order convergence theory for weakly-convex-weakly-concave min-max problems

MaRDI QIDQ5159451zbMATH OpenFDO

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

Publication date 27 October 2021

Full work available at URL https://arxiv.org/abs/1810.10207, https://jmlr.csail.mit.edu/papers/v22/20-533.html

zbMATH Keywords

variational inequalitymin-maxfirst-order convergencegenerative adversarial netsweakly-convex-weakly-concave

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Weakly-convex-concave min-max optimization: provable algorithms and applications in machine learning
• Optimality Conditions for Nonsmooth Nonconvex-Nonconcave Min-Max Problems and Generative Adversarial Networks
• Alternating Proximal-Gradient Steps for (Stochastic) Nonconvex-Concave Minimax Problems
• Two steps at a time-taking GAN training in stride with Tseng's method
• The landscape of the proximal point method for nonconvex-nonconcave minimax optimization

Cites work

• scientific article; zbMATH DE number 3534286 (Why is no real title available?)
• scientific article; zbMATH DE number 2159409 (Why is no real title available?)
• A New Projection Method for Variational Inequality Problems
• A first-order primal-dual algorithm for convex problems with applications to imaging
• Accelerated gradient methods for nonconvex nonlinear and stochastic programming
• An efficient primal dual prox method for non-smooth optimization
• Extragradient Method with Variance Reduction for Stochastic Variational Inequalities
• Finite-dimensional variational inequality and nonlinear complementarity problems: A survey of theory, algorithms and applications
• Monotone (nonlinear) operators in Hilbert space
• Monotone Operators and the Proximal Point Algorithm
• Most tensor problems are NP-hard
• On some non-linear elliptic differential functional equations
• On the convergence properties of non-Euclidean extragradient methods for variational inequalities with generalized monotone operators
• Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
• Robust Stochastic Approximation Approach to Stochastic Programming
• Robust linear least squares regression
• Saddle-point dynamics: conditions for asymptotic stability of saddle points
• Solving strongly monotone variational and quasi-variational inequalities
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• The proximal point method for nonmonotone variational inequalities
• Unified framework of extragradient-type methods for pseudomonotone variational inequalities.

Cited in

(6)

• First-order Convergence Theory for Weakly-Convex-Weakly-Concave Min-max Problems
• Alternating Proximal-Gradient Steps for (Stochastic) Nonconvex-Concave Minimax Problems
• Optimality Conditions for Nonsmooth Nonconvex-Nonconcave Min-Max Problems and Generative Adversarial Networks
• Decentralized Gradient Descent Maximization Method for Composite Nonconvex Strongly-Concave Minimax Problems
• A quasi-Newton subspace trust region algorithm for nonmonotone variational inequalities in adversarial learning over box constraints
• Perseus: a simple and optimal high-order method for variational inequalities

Describes a project that uses

Uses Software

• SBEED
• Wasserstein GAN

This page was built for publication: First-order convergence theory for weakly-convex-weakly-concave min-max problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5159451)