EXOTIC: An Exact, Optimistic, Tree-Based Algorithm for Min-Max Optimization

ArXi:2508.12479v2 Announce Type: replace-cross Min-max optimization arises in many domains such as game theory, adversarial machine learning, etc. For these problems, gradient-based methods are well understood and enjoy strong guarantees. However, in the absence of convexity or concavity, existing approaches study convergence to an approximate saddle point or first-order stationary points, which may be arbitrarily far from global optima.