The proximal gradient method

Overview

ABSTRACT

The proximal gradient method is a splitting algorithm for the minimization of the sum of two convex functions, one of which is smooth. It has applications in areas such as mechanics, inverse problems, machine learning, image reconstruction, variational inequalities, statistics, operations research, and optimal transportation. Its formalism encompasses a wide variety of numerical methods in optimization such as gradient descent, projected gradient, iterative thresholding, alternating projections, the constrained Landweber method, as well as various algorithms in statistics and sparse data analysis. This paper aims at providing an account of the main properties of the proximal gradient method and to discuss some of its applications.

Read this article from a comprehensive knowledge base, updated and supplemented with articles reviewed by scientific committees.

Read the article

AUTHOR

Patrick L. COMBETTES: North Carolina State University - Department of Mathematics - Raleigh, NC 27695, United States

INTRODUCTION

Notations. $H$ , $G$ and $G_{k}$ are Euclidean spaces, i.e. real Hilbertian spaces of finite dimension. Note $〈 \cdot | \cdot 〉$ their scalar product and $‖ \cdot ‖$ the associated norm. A function $f : H \to] – \infty, + \infty]$ is clean if $dom f = {x \in H | f (x) < + \infty} \neq \emptyset$ . The class of lower, convex and proper semicontinuous functions of $H$ in $] – \infty, + \infty]$ is noted $Γ_{0} (H)$ . Finally, $ir C$ ...

You do not have access to this resource.

Exclusive to subscribers. 97% yet to be discovered!

You do not have access to this resource. Click here to request your free trial access!

Already subscribed? Log in!

KEYWORDS

splitting algorithm | convex function | numerical methods in optimization | gradient descent

Ongoing reading
The proximal gradient method

Mathematical framework

Article included in this offer

"Mathematics"

( 165 articles )

Complete knowledge base

Updated and enriched with articles validated by our scientific committees

Services

A set of exclusive tools to complement the resources

View offer details

Bibliography

(1) - ACKER (F.), PRESTEL (M.A.) - Convergence d'un schéma de minimisation alternée, - Ann. Fac. Sci. Toulouse V. Sér. Math., vol. 2, pp. 1–9 (1980).
(2) - ATTOUCH (H.), BOLTE (J.), REDONT (P.), SOUBEYRAN (A.) - Alternating proximal algorithms for weakly coupled...

You do not have access to this resource.

Exclusive to subscribers. 97% yet to be discovered!

You do not have access to this resource. Click here to request your free trial access!

Already subscribed? Log in!

The Proximal Gradient Method

Bibliography