Mirror Descent-Ascent for mean-field min-max problems
math.OC, cs.LG, math.PR
Submitted: 2024-02-12
Updated: 2026-11-05
Comments: Accepted at NeurIPS 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Human Alignment of Large Language Models through Online Preference Optimisation
- Improved Training of Wasserstein GANs
- Trainability and Accuracy of Neural Networks: An Interacting Particle System Approach
- Mirror Descent Policy Optimization
- On adversarial robustness and the use of Wasserstein ascent-descent dynamics to enforce it
- An Exponentially Converging Particle Method for the Mixed Nash Equilibrium of Continuous Games
Related papers
- An Accelerated Proximal Gradient Method for Bures-Wasserstein Space
- FOMTools: Development and AI-Assisted Code Generation for First-Order Methods
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Dynamic Service Recommendation with Congestion-Dependent Joining: Near-Optimal and Constant-Factor Approximation Algorithms
- Integrating Learning and Optimization for Open Transport Capacity Pooling under Disruption
- Zeroth-Order Gradient Estimators under Decision-Dependent Noise