Approximate first-order primal-dual algorithms for the saddle point problems

2020 ◽  
pp. 1
Author(s):  
Fan Jiang ◽  
Xingju Cai ◽  
Zhongming Wu ◽  
Deren Han
Author(s):  
Renbo Zhao

We develop stochastic first-order primal-dual algorithms to solve a class of convex-concave saddle-point problems. When the saddle function is strongly convex in the primal variable, we develop the first stochastic restart scheme for this problem. When the gradient noises obey sub-Gaussian distributions, the oracle complexity of our restart scheme is strictly better than any of the existing methods, even in the deterministic case. Furthermore, for each problem parameter of interest, whenever the lower bound exists, the oracle complexity of our restart scheme is either optimal or nearly optimal (up to a log factor). The subroutine used in this scheme is itself a new stochastic algorithm developed for the problem where the saddle function is nonstrongly convex in the primal variable. This new algorithm, which is based on the primal-dual hybrid gradient framework, achieves the state-of-the-art oracle complexity and may be of independent interest.


2014 ◽  
Vol 24 (4) ◽  
pp. 1779-1814 ◽  
Author(s):  
Yunmei Chen ◽  
Guanghui Lan ◽  
Yuyuan Ouyang

2021 ◽  
Vol 31 (2) ◽  
pp. 1299-1329
Author(s):  
Erfan Yazdandoost Hamedani ◽  
Necdet Serhat Aybat

Sign in / Sign up

Export Citation Format

Share Document