Stochastic Primal-Dual Three Operator Splitting with Arbitrary Sampling and Preconditioning

Junqi Tang, Matthias Ehrhardt, Carola-Bibiane Schönlieb

Research output: Working paper / PreprintPreprint

54 Downloads (Pure)

Abstract

In this work we propose a stochastic primal-dual preconditioned three-operator splitting algorithm for solving a class of convex three-composite optimization problems. Our proposed scheme is a direct three-operator splitting extension of the SPDHG algorithm [Chambolle et al. 2018]. We provide theoretical convergence analysis showing ergodic O(1/K) convergence rate, and demonstrate the effectiveness of our approach in imaging inverse problems.
Original languageUndefined/Unknown
Publication statusPublished - 2 Aug 2022

Keywords

  • math.OC
  • cs.LG
  • eess.IV

Cite this