min-max optimization
An optimization strategy that seeks to minimize the maximum loss or cost, often used in adversarial settings like game theory or training generative adversarial networks (GANs), where two agents compete against each other.
- Bilevel Optimization for Adversarial Learning Problems: Sharpness, Generation, and Beyond
- Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems
- Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty
- Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback
- SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
- Semi-infinite Nonconvex Constrained Min-Max Optimization
- The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games
- Unlearning-Aware Minimization