Optimized methods for composite optimization: a reduction perspective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bok, Jinho, Altschuler, Jason M.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911029898772480
author Bok, Jinho
Altschuler, Jason M.
author_facet Bok, Jinho
Altschuler, Jason M.
contents Recent advances in convex optimization have leveraged computer-assisted proofs to develop optimized first-order methods that improve over classical algorithms. However, each optimized method is specially tailored for a particular problem setting, and it is a well-documented challenge to extend optimized methods to other settings due to their highly bespoke design and analysis. We provide a general framework that derives optimized methods for composite optimization directly from those for unconstrained smooth optimization. The derived methods naturally extend the original methods, generalizing how proximal gradient descent extends gradient descent. The key to our result is certain algebraic identities that provide a unified and straightforward way of extending convergence analyses from unconstrained to composite settings. As concrete examples, we apply our framework to establish (1) the phenomenon of stepsize acceleration for proximal gradient descent; (2) a convergence rate for the proximal optimized gradient method which is faster than FISTA; (3) a new method that improves the state-of-the-art rate for minimizing gradient norm in the composite setting.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23756
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Optimized methods for composite optimization: a reduction perspective
Bok, Jinho
Altschuler, Jason M.
Optimization and Control
Data Structures and Algorithms
Recent advances in convex optimization have leveraged computer-assisted proofs to develop optimized first-order methods that improve over classical algorithms. However, each optimized method is specially tailored for a particular problem setting, and it is a well-documented challenge to extend optimized methods to other settings due to their highly bespoke design and analysis. We provide a general framework that derives optimized methods for composite optimization directly from those for unconstrained smooth optimization. The derived methods naturally extend the original methods, generalizing how proximal gradient descent extends gradient descent. The key to our result is certain algebraic identities that provide a unified and straightforward way of extending convergence analyses from unconstrained to composite settings. As concrete examples, we apply our framework to establish (1) the phenomenon of stepsize acceleration for proximal gradient descent; (2) a convergence rate for the proximal optimized gradient method which is faster than FISTA; (3) a new method that improves the state-of-the-art rate for minimizing gradient norm in the composite setting.
title Optimized methods for composite optimization: a reduction perspective
topic Optimization and Control
Data Structures and Algorithms
url https://arxiv.org/abs/2506.23756