Two-timescale gradient descent ascent algorithms for nonconvex minimax optimization
From MaRDI portal
The authors introduce and investigate two-timescale gradient descent ascent type algorithms for solving structured minimax problems, where nonconvexity in the first variable and concavity in the second variable are imposed (the underlying set is convex and bounded). Theoretical bounds on the complexity for solving smooth and nonsmooth problems are derived as well.
Cites work
- A unified single-loop alternating gradient projection algorithm for nonconvex-concave and convex-nonconcave minimax problems
- Algorithmic Game Theory
- Alternating Proximal-Gradient Steps for (Stochastic) Nonconvex-Concave Minimax Problems
- An Accelerated Inexact Proximal Point Method for Solving Nonconvex-Concave Min-Max Problems
- An iterative method of solving a game
- Convergence rate of \(\mathcal{O}(1/k)\) for optimistic gradient and extragradient methods in smooth convex-concave saddle point problems
- Convergence Rates in Forward--Backward Splitting
- Cycles in adversarial regularized learning
- Distributed Sparse Linear Regression
- Efficient search of first-order Nash equilibria in nonconvex-concave smooth min-max problems
- First-order convergence theory for weakly-convex-weakly-concave min-max problems
- Gradient methods for minimizing composite functions
- 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 46303 (Why is no real title available?)
- scientific article; zbMATH DE number 3534286 (Why is no real title available?)
- scientific article; zbMATH DE number 1243371 (Why is no real title available?)
- scientific article; zbMATH DE number 7625189 (Why is no real title available?)
- scientific article; zbMATH DE number 3247810 (Why is no real title available?)
- Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications
- Last-iterate convergence: zero-sum games and constrained min-max optimization
- Lectures on convex optimization
- On general minimax theorems
- Optimality Conditions for Nonsmooth Nonconvex-Nonconcave Min-Max Problems and Generative Adversarial Networks
- Prediction, Learning, and Games
- Projected subgradient methods with non-Euclidean distances for non-differentiable convex minimization and variational inequalities
- Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
- Robustness and regularization of support vector machines
- Saddle-point dynamics: conditions for asymptotic stability of saddle points
- Solutions of Saddle Value Problems by Differential Equations
- Solving variational inequalities with stochastic mirror-prox algorithm
- Some NP-complete problems in quadratic and nonlinear programming
- Stochastic model-based minimization of weakly convex functions
- Subgradient methods for saddle-point problems
- The complexity of constrained min-max optimization
- The landscape of the proximal point method for nonconvex-nonconcave minimax optimization
- Zur Theorie der Gesellschaftsspiele.
Cited in
(5)- Policy gradient algorithms for robust MDPs with nonrectangular uncertainty sets
- Inexact zeroth-order nonsmooth and nonconvex stochastic composite optimization and applications
- Adaptive method for saddle point problems with a generalization of smoothness property
- Nonexpansive mappings in two-time-scale stochastic approximation: finite-time analysis
- Gradient sampling algorithm for subsmooth functions
This page was built for publication: Two-timescale gradient descent ascent algorithms for nonconvex minimax optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6982689)
