A stochastic primal-dual splitting algorithm with variance reduction for composite optimization problems

This paper revisits the generic structured primal-dual problem involving the infimal convolution in real Hilbert spaces. For this purpose, we develop a stochastic primal-dual splitting with variance reduction for solving this generic problem. Weak almost sure convergence of the iterates is proved. The linear convergence rate of the primal-dual gap is obtained under an additional condition like the strong convexity.

Article

Download

View A stochastic primal-dual splitting algorithm with variance reduction for composite optimization problems