Linear Last-iterate Convergence in Constrained Saddle-point OptimizationDownload PDF

Sep 28, 2020 (edited Mar 16, 2021)ICLR 2021 PosterReaders: Everyone
  • Keywords: Saddle-point Optimization, Optimistic Mirror Decent, Optimistic Gradient Descent Ascent, Optimistic Multiplicative Weights Update, Last-iterate Convergence, Game Theory
  • Abstract: Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weights Update (OMWU) for saddle-point optimization have received growing attention due to their favorable last-iterate convergence. However, their behaviors for simple bilinear games over the probability simplex are still not fully understood --- previous analysis lacks explicit convergence rates, only applies to an exponentially small learning rate, or requires additional assumptions such as the uniqueness of the optimal solution. In this work, we significantly expand the understanding of last-iterate convergence for OGDA and OMWU in the constrained setting. Specifically, for OMWU in bilinear games over the simplex, we show that when the equilibrium is unique, linear last-iterate convergence is achievable with a constant learning rate, which improves the result of (Daskalakis & Panageas, 2019) under the same assumption. We then significantly extend the results to more general objectives and feasible sets for the projected OGDA algorithm, by introducing a sufficient condition under which OGDA exhibits concrete last-iterate convergence rates with a constant learning rate. We show that bilinear games over any polytope satisfy this condition and OGDA converges exponentially fast even without the unique equilibrium assumption. Our condition also holds for strongly-convex-strongly-concave functions, recovering the result of (Hsieh et al., 2019). Finally, we provide experimental results to further support our theory.
  • Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
  • One-sentence Summary: We prove Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weights Update (OMWU) converge exponentially fast to the Nash equilibrium in the sense of last-iterate in various game settings including matrix games.
18 Replies