Last-Iterate Convergence in Constrained Min-Max Optimization - SOS to the Rescue

Explore a lecture on last-iterate convergence in constrained min-max optimization, featuring Yang Cai from Yale University. Delve into the application of Sum of Squares (SOS) techniques to address challenges in adversarial machine learning approaches. Gain insights into robust mechanism design and its implications for machine learning algorithms. Examine the intersection of optimization theory and adversarial learning, uncovering strategies to enhance the convergence of iterative processes in constrained environments.

Last-Iterate Convergence in Constrained Min-Max Optimization: SOS to the Rescue