Stochastic Primal-Dual Three Operator Splitting Algorithm with Extension to Equivariant Regularization-by-Denoising

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Junqi, Ehrhardt, Matthias, Schönlieb, Carola-Bibiane
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913736418131968
author Tang, Junqi
Ehrhardt, Matthias
Schönlieb, Carola-Bibiane
author_facet Tang, Junqi
Ehrhardt, Matthias
Schönlieb, Carola-Bibiane
contents In this work we propose a stochastic primal-dual three-operator splitting algorithm (TOS-SPDHG) 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. Moreover, we further propose TOS-SPDHG-RED and TOS-SPDHG-eRED which utilizes the regularization-by-denoising (RED) framework to leverage pretrained deep denoising networks as priors.
format Preprint
id arxiv_https___arxiv_org_abs_2208_01631
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Stochastic Primal-Dual Three Operator Splitting Algorithm with Extension to Equivariant Regularization-by-Denoising
Tang, Junqi
Ehrhardt, Matthias
Schönlieb, Carola-Bibiane
Optimization and Control
Machine Learning
Image and Video Processing
In this work we propose a stochastic primal-dual three-operator splitting algorithm (TOS-SPDHG) 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. Moreover, we further propose TOS-SPDHG-RED and TOS-SPDHG-eRED which utilizes the regularization-by-denoising (RED) framework to leverage pretrained deep denoising networks as priors.
title Stochastic Primal-Dual Three Operator Splitting Algorithm with Extension to Equivariant Regularization-by-Denoising
topic Optimization and Control
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2208.01631