V. Cevher, G. Piliouras, Ryann Sim, Stratis Skoulakis
{"title":"简化最小-最大优化:通过收缩映射逼近近点方法","authors":"V. Cevher, G. Piliouras, Ryann Sim, Stratis Skoulakis","doi":"10.48550/arXiv.2301.03931","DOIUrl":null,"url":null,"abstract":"In this paper we present a first-order method that admits near-optimal convergence rates for convex/concave min-max problems while requiring a simple and intuitive analysis. Similarly to the seminal work of Nemirovski and the recent approach of Piliouras et al. in normal form games, our work is based on the fact that the update rule of the Proximal Point method (PP) can be approximated up to accuracy $\\epsilon$ with only $O(\\log 1/\\epsilon)$ additional gradient-calls through the iterations of a contraction map. Then combining the analysis of (PP) method with an error-propagation analysis we establish that the resulting first order method, called Clairvoyant Extra Gradient, admits near-optimal time-average convergence for general domains and last-iterate convergence in the unconstrained case.","PeriodicalId":93491,"journal":{"name":"Proceedings of the SIAM Symposium on Simplicity in Algorithms (SOSA)","volume":"136 1","pages":"192-206"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"Min-Max Optimization Made Simple: Approximating the Proximal Point Method via Contraction Maps\",\"authors\":\"V. Cevher, G. Piliouras, Ryann Sim, Stratis Skoulakis\",\"doi\":\"10.48550/arXiv.2301.03931\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper we present a first-order method that admits near-optimal convergence rates for convex/concave min-max problems while requiring a simple and intuitive analysis. Similarly to the seminal work of Nemirovski and the recent approach of Piliouras et al. in normal form games, our work is based on the fact that the update rule of the Proximal Point method (PP) can be approximated up to accuracy $\\\\epsilon$ with only $O(\\\\log 1/\\\\epsilon)$ additional gradient-calls through the iterations of a contraction map. Then combining the analysis of (PP) method with an error-propagation analysis we establish that the resulting first order method, called Clairvoyant Extra Gradient, admits near-optimal time-average convergence for general domains and last-iterate convergence in the unconstrained case.\",\"PeriodicalId\":93491,\"journal\":{\"name\":\"Proceedings of the SIAM Symposium on Simplicity in Algorithms (SOSA)\",\"volume\":\"136 1\",\"pages\":\"192-206\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the SIAM Symposium on Simplicity in Algorithms (SOSA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2301.03931\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the SIAM Symposium on Simplicity in Algorithms (SOSA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2301.03931","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4
摘要
本文给出了一种一阶方法,该方法允许凸/凹最小-最大问题的近似最优收敛速率,同时需要简单直观的分析。与Nemirovski的开创性工作和Piliouras等人最近在正常形式游戏中的方法类似,我们的工作是基于这样一个事实,即Proximal Point method (PP)的更新规则可以通过收缩地图的迭代仅$O(\log 1/\epsilon)$额外的梯度调用来近似达到$\epsilon$的精度。然后将(PP)方法的分析与误差传播分析相结合,证明了所得到的一阶方法Clairvoyant Extra Gradient在一般情况下具有近似最优的时间平均收敛性,在无约束情况下具有最后迭代收敛性。
Min-Max Optimization Made Simple: Approximating the Proximal Point Method via Contraction Maps
In this paper we present a first-order method that admits near-optimal convergence rates for convex/concave min-max problems while requiring a simple and intuitive analysis. Similarly to the seminal work of Nemirovski and the recent approach of Piliouras et al. in normal form games, our work is based on the fact that the update rule of the Proximal Point method (PP) can be approximated up to accuracy $\epsilon$ with only $O(\log 1/\epsilon)$ additional gradient-calls through the iterations of a contraction map. Then combining the analysis of (PP) method with an error-propagation analysis we establish that the resulting first order method, called Clairvoyant Extra Gradient, admits near-optimal time-average convergence for general domains and last-iterate convergence in the unconstrained case.