Unified linear convergence of first-order primal-dual algorithms for saddle point problems

Unified linear convergence of first-order primal-dual algorithms for saddle point problems
复制标题

鞍点问题一阶原对偶算法的统一线性收敛

DOI:
10.1007/s11590-021-01832-y
复制
发表时间:
2022-01
影响因子:
1.6
通讯作者:
Hongchao Zhang
Hongchao Zhang
中科院分区:
数学4区
文献类型:
--
作者:
Fan Jiang;Zhongming Wu;Xingju Cai;Hongchao Zhang

文献摘要

参考文献

相似文献

在本文中,我们研究了几种著名的一阶原始 - 对偶方法用于解决一类凸 - 凹鞍点问题的线性收敛性。我们首先统一了这些方法的收敛性分析,并证明了$O(1/N)$的收敛速率。
In this paper, we study the linear convergence of several well-known first-order primal-dual methods for solving a class of convex-concave saddle point problems. We first unify the convergence analysis of these methods and prove theO(1/N) convergence rates of the primal-dual gap generated by these methods in the ergodic sense, whereNcounts the number of iterations. Under a mild calmness condition, we further establish the global Q-linear convergence rate of the distances between the iterates generated by these methods and the solution set, and show the R-linear rate of the iterates in the nonergodic sense. Moreover, we demonstrate that the matrix games, fused lasso and constrained TV-image restoration models as application examples satisfy this calmness condition. Numerical experiments on fused lasso demonstrate the linear rates for these methods.
DOI: 10.1093/pcmedi/pbac012
发表时间: 2022-05-13
影响因子: 5.3
作者:
通讯作者: --
DOI: 10.1287/moor.2017.0875
发表时间: 2017-12
影响因子: 1.7
作者:
Deren Han;Defeng Sun;Liwei Zhang
通讯作者: Liwei Zhang
DOI: 10.1186/s13663-016-0543-2
发表时间: 2015-12
影响因子: --
作者:
Chen Peijun;Huang Jianguo;Zhang Xiaoqun
通讯作者: Zhang Xiaoqun
DOI: 10.1007/s10107-018-1321-1
发表时间: 2018-08
影响因子: 2.7
作者:
D. O’Connor;L. Vandenberghe
通讯作者: D. O’Connor;L. Vandenberghe
DOI: 10.1051/m2an/197509r200411
发表时间: 1975
期刊: --
影响因子: --
作者:
R. Glowinski;A. Marroco
通讯作者: R. Glowinski;A. Marroco