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
中科院分区:
文献类型:
--
作者:
Fan Jiang;Zhongming Wu;Xingju Cai;Hongchao Zhang
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.
登录
查看更多内容
影响因子:
5.3
作者:
通讯作者:
--
影响因子:
1.7
作者:
Deren Han;Defeng Sun;Liwei Zhang
通讯作者:
Liwei Zhang
影响因子:
--
作者:
Chen Peijun;Huang Jianguo;Zhang Xiaoqun
通讯作者:
Zhang Xiaoqun
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