arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.20918math.OC
收藏

无镜像的近端方法

Mirror-Free Proximal Methods

Purdue University(普渡大学)

Abhijeet Vyas, Brian Bullins

AI总结:

本文提出了一种无需镜像映射的近端方法,分析了其在相对光滑性和 Lipschitz 性下的收敛性,并展示了其在二阶和三阶光滑 min-max 优化中的应用。

摘要:

我们提出了一种无镜像的镜像近端(MFMP)算法,扩展了 Nemirovski (2004) 的经典方法,允许在无需显式镜像映射的情况下进行近端更新。我们进一步分析了在适当相对光滑性和相对 Lipschitz 性下的收敛性,为此引入了更一般的势函数来放松标准 Bregman 发散性。最后,我们展示了强单调性变体的方法如何解决在二阶和三阶光滑 min-max 优化中出现的正则化泰勒展开子问题。

英文摘要:

We present a \emph{mirror-free} mirror prox (MFMP) algorithm, which extends the classic approach of Nemirovski (2004) to allow for proximal-like updates without the explicit need for a mirror map. We further analyze the convergence of our method under suitable notions of relative smoothness and relative Lipschitzness, for which we introduce a relaxation of the standard Bregman divergence in terms of more general potential operators. Finally, we show how a strongly monotone variant of our method allows us to solve regularized Taylor-expansion subproblems that appear in both second- and third-order smooth min-max optimization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑