Stochastic primal dual fixed point method for composite optimization

2020/04/20 by YaNanZhu, XiaoqunZhang
Mathematics · Computer Science · #Advanced Optimization Algorithms Research #Optimization and Variational Analysis #Advanced Multi-Objective Optimization Algorithms

paper · pdf · doi:10.48550/arxiv.2004.09071

Abstract

In this paper we propose a stochastic primal dual fixed point method (SPDFP) for solving the sum of two proper lower semi-continuous convex function and one of which is composite. The method is based on the primal dual fixed point method (PDFP) proposed in [7] that does not require subproblem solving. Under some mild condition, the convergence is established based on two sets of assumptions: bounded and unbounded gradients and the convergence rate of the expected error of iterate is of the order O(k^α) where k is iteration number and α∈ (0, 1]. Finally, numerical examples on graphic Lasso and logistic regressions are given to demonstrate the effectiveness of the proposed algorithm.

Related

• A Stochastic Variance Reduced Primal Dual Fixed Point Method For Linearly Constrained Separable Optimization
• A Fully Stochastic Primal-Dual Algorithm
• A stochastic coordinate descent splitting primal-dual fixed point algorithm and applications to large-scale composite optimization
• A stochastic coordinate descent primal-dual algorithm with dynamic stepsize for large-scale composite optimization
• Optimal Primal-Dual Algorithm with Last iterate Convergence Guarantees for Stochastic Convex Optimization Problems