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 1802.01504math.OCcs.LGstat.ML
收藏

非强凸性凹凸鞍点问题原-对偶梯度法的线性收敛

Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity

Carnegie Mellon University(卡内基梅隆大学);Princeton University(普林斯顿大学)

Simon S. Du, Wei Hu

摘要:

本文考虑凸-凹鞍点问题$\min_{x}\max_{y} f(x)+y^\top A x-g(y)$,其中$f$是光滑凸的,$g$是光滑强凸的.证明了当耦合矩阵$A$具有满列秩时,即使$f$不是强凸的,vanilla原-对偶梯度法也能达到线性收敛.我们的结果推广了以前的工作,要么要求$f$和$g$是二次函数,或要求$f$和$g$的邻近映射。我们采用了一种新的分析技术,在每次迭代中使用“鬼”更新作为参考,并显示在原始-对偶梯度法的迭代收敛到这个“鬼”序列。利用同样的技巧,我们进一步分析了具有有限和结构的凸凹鞍点问题的原始-对偶随机方差约减梯度(SVRG)方法。

英文摘要:

We consider the convex-concave saddle point problem $\min_{x}\max_{y} f(x)+y^\top A x-g(y)$ where $f$ is smooth and convex and $g$ is smooth and strongly convex. We prove that if the coupling matrix $A$ has full column rank, the vanilla primal-dual gradient method can achieve linear convergence even if $f$ is not strongly convex. Our result generalizes previous work which either requires $f$ and $g$ to be quadratic functions or requires proximal mappings for both $f$ and $g$. We adopt a novel analysis technique that in each iteration uses a "ghost" update as a reference, and show that the iterates in the primal-dual gradient method converge to this "ghost" sequence. Using the same technique we further give an analysis for the primal-dual stochastic variance reduced gradient (SVRG) method for convex-concave saddle point problems with a finite-sum structure.

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。

↑