Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Application
Type
PreprintKAUST Department
Computer Science ProgramComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Extreme Computing Research Center
Visual Computing Center (VCC)
Date
2017-06-15Permanent link to this record
http://hdl.handle.net/10754/626553
Metadata
Show full item recordAbstract
We propose a stochastic extension of the primal-dual hybrid gradient algorithm studied by Chambolle and Pock in 2011 to solve saddle point problems that are separable in the dual variable. The analysis is carried out for general convex-concave saddle point problems and problems that are either partially smooth / strongly convex or fully smooth / strongly convex. We perform the analysis for arbitrary samplings of dual variables, and obtain known deterministic results as a special case. Several variants of our stochastic method significantly outperform the deterministic variant on a variety of imaging tasks.Publisher
arXivarXiv
1706.04957Additional Links
http://arxiv.org/abs/1706.04957v1http://arxiv.org/pdf/1706.04957v1