AI RESEARCH
When and Why is Optimistic Multiplicative Weights Slow? The Geometry of Energy Dissipation
arXiv CS.LG
•
ArXi:2605.13242v1 Announce Type: cross This paper studies the convergence of the Optimistic Multiplicative Weights Update algorithm (OMWU) in two player zero-sum games. Recent works have identified instances on which the last-iterate of OMWU can converge arbitrarily slowly, but understanding when and why this slow convergence occurs has remained open. In this work, we develop a new analysis framework that gives sharp, quantitative explanations for this behavior.