Saved in:
Bibliographic Details
Main Authors: Driggs, Derek, Ehrhardt, Matthias J., Schönlieb, Carola-Bibiane, Tang, Junqi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.17100
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916176380035072
author Driggs, Derek
Ehrhardt, Matthias J.
Schönlieb, Carola-Bibiane
Tang, Junqi
author_facet Driggs, Derek
Ehrhardt, Matthias J.
Schönlieb, Carola-Bibiane
Tang, Junqi
contents The Condat-Vũ algorithm is a widely used primal-dual method for optimizing composite objectives of three functions. Several algorithms for optimizing composite objectives of two functions are special cases of Condat-Vũ, including proximal gradient descent (PGD). It is well-known that PGD exhibits suboptimal performance, and a simple adjustment to PGD can accelerate its convergence rate from $\mathcal{O}(1/T)$ to $\mathcal{O}(1/T^2)$ on convex objectives, and this accelerated rate is optimal. In this work, we show that a simple adjustment to the Condat-Vũ algorithm allows it to recover accelerated PGD (APGD) as a special case, instead of PGD. We prove that this accelerated Condat--Vũ algorithm achieves optimal convergence rates and significantly outperforms the traditional Condat-Vũ algorithm in regimes where the Condat--Vũ algorithm approximates the dynamics of PGD. We demonstrate the effectiveness of our approach in various applications in machine learning and computational imaging.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17100
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Practical Acceleration of the Condat-Vũ Algorithm
Driggs, Derek
Ehrhardt, Matthias J.
Schönlieb, Carola-Bibiane
Tang, Junqi
Optimization and Control
The Condat-Vũ algorithm is a widely used primal-dual method for optimizing composite objectives of three functions. Several algorithms for optimizing composite objectives of two functions are special cases of Condat-Vũ, including proximal gradient descent (PGD). It is well-known that PGD exhibits suboptimal performance, and a simple adjustment to PGD can accelerate its convergence rate from $\mathcal{O}(1/T)$ to $\mathcal{O}(1/T^2)$ on convex objectives, and this accelerated rate is optimal. In this work, we show that a simple adjustment to the Condat-Vũ algorithm allows it to recover accelerated PGD (APGD) as a special case, instead of PGD. We prove that this accelerated Condat--Vũ algorithm achieves optimal convergence rates and significantly outperforms the traditional Condat-Vũ algorithm in regimes where the Condat--Vũ algorithm approximates the dynamics of PGD. We demonstrate the effectiveness of our approach in various applications in machine learning and computational imaging.
title Practical Acceleration of the Condat-Vũ Algorithm
topic Optimization and Control
url https://arxiv.org/abs/2403.17100