SILO: Recent Advances in Min-max Optimization: Convergence Guarantees and Practical Performance
Abstract: Min-max optimization plays a prominent role in game theory, statistics, economics, finance, and engineering. It has recently received significant attention, especially in the machine learning community, where adversarial training of neural networks, multi-agent reinforcement learning, and distributionally robust learning are formulated as structured min-max optimization problems. Stochastic Gradient Descent Ascent …