Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications
Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications is a scholarly work, published in 2018 in ''SIAM Journal on Optimization''. The main subjects of the publication include point, mathematics, extension, Markov chain Monte Carlo, computer science, convex optimization, mathematical optimization, mountain saddle, separable space, variable, regular polygon, compressed sensing, applied mathematics, machine learning, Proximal Gradient Methods, dual, saddle point, and algorithm. The authors propose a stochastic extension of the primal-dual hybrid gradient\nalgorithm studied by Chambolle and Pock in 2011 to solve saddle point problems\nthat are separable in the dual variable.