Motivated by applications in Game Theory, Optimization, and Generative Adversarial Networks, recent work of Daskalakis et al \cite{DISZ17} and follow-up work of Liang and Stokes \cite{LiangS18} have established that a variant of the widely used Gradient Descent/Ascent procedure, called "Optimistic Gradient Descent/Ascent (OGDA)", exhibits last-iterate convergence to saddle points in {\em unconstrained} convex-concave min-max optimization problems. We show that the same holds true in the more general problem of {\em constrained} min-max optimization under a variant of the no-regret Multiplicative-Weights-Update method called "Optimistic Multiplicative-Weights Update (OMWU)". This answers an open question of Syrgkanis et al \cite{SALS15}. The proof of our result requires fundamentally different techniques from those that exist in no-regret learning literature and the aforementioned papers. We show that OMWU monotonically improves the Kullback-Leibler divergence of the current iterate to the (appropriately normalized) min-max solution until it enters a neighborhood of the solution. Inside that neighborhood we show that OMWU is locally (asymptotically) stable converging to the exact solution. We believe that our techniques will be useful in the analysis of the last iterate of other learning algorithms.
翻译:在游戏理论、优化和创造反向网络的应用、 Daskalakis 等人最近的工作{DISZ17} 以及Liang 和 Stokes\ cite{LiangS18} 的后续工作的推动下,运用了游戏理论、优化和创造反向网络的应用程序,Daskalakis 等公司最近的工作和Liang 和 Stokes\ cite{LiangS18} 的后续工作已经确定,广泛使用的梯度梯度源/感光度程序的变异,称为“OWWWU(OGBDA) ”, 是一个开放的Syrgkanis 和al\cite SALS15} 问题。 证明我们的结果需要与目前不折叠加的硬化区际法 一样的技术, 也就是在不折叠变法的 法 下, 微振平流- Wereto acal labal road road road road road road road room subal subal sublex 之前, 显示, 我们最后需要从不折变现的变现的硬化的硬化的硬化的软化的软化的软化的文献和变化的文献和变化的论文。