2016/02/25 by Lorenzo Rosasco, Silvia Villa, Rosasco, Lorenzo +3
Mathematics · #47H05 #49M27 #49M29 #90C25 #FOS: Mathematics #Optimization and Control (math.OC) #math.OC #msc:47H05 #msc:49M27 #msc:49M29 #msc:90C25
paper · pdf · doi:10.48550/arxiv.1602.07872
arxiv created 2016/02/25 · arxiv updated 2016/02/26
We investigate the convergence properties of a stochastic primal-dual splitting algorithm for solving structured monotone inclusions involving the sum of a cocoercive operator and a composite monotone operator. The proposed method is the stochastic extension to monotone inclusions of a proximal method studied in \em Y. Drori, S. Sabach, and M. Teboulle, A simple algorithm for a class of nonsmooth convex-concave saddle-point problems, 2015 and \em I. Loris and C. Verhoeven, On a generalization of the iterative soft-thresholding algorithm for the case of non-separable penalty, 2011 for saddle point problems. It consists in a forward step determined by the stochastic evaluation of the cocoercive operator, a backward step in the dual variables involving the resolvent of the monotone operator, and an additional forward step using the stochastic evaluation of the cocoercive introduced in the first step. We prove weak almost sure convergence of the iterates by showing that the primal-dual sequence generated by the method is stochastic quasi Fejér-monotone with respect to the set of zeros of the considered primal and dual inclusions. Additional results on ergodic convergence in expectation are considered for the special case of saddle point models.