Saved in:
Bibliographic Details
Main Authors: Park, Chanwoo, Ryu, Ernest K.
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2110.11035
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910378089250816
author Park, Chanwoo
Ryu, Ernest K.
author_facet Park, Chanwoo
Ryu, Ernest K.
contents In this work, we present a novel algorithm design methodology that finds the optimal algorithm as a function of inequalities. Specifically, we restrict convergence analyses of algorithms to use a prespecified subset of inequalities, rather than utilizing all true inequalities, and find the optimal algorithm subject to this restriction. This methodology allows us to design algorithms with certain desired characteristics. As concrete demonstrations of this methodology, we find new state-of-the-art accelerated first-order gradient methods using randomized coordinate updates and backtracking line searches.
format Preprint
id arxiv_https___arxiv_org_abs_2110_11035
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Optimal First-Order Algorithms as a Function of Inequalities
Park, Chanwoo
Ryu, Ernest K.
Optimization and Control
In this work, we present a novel algorithm design methodology that finds the optimal algorithm as a function of inequalities. Specifically, we restrict convergence analyses of algorithms to use a prespecified subset of inequalities, rather than utilizing all true inequalities, and find the optimal algorithm subject to this restriction. This methodology allows us to design algorithms with certain desired characteristics. As concrete demonstrations of this methodology, we find new state-of-the-art accelerated first-order gradient methods using randomized coordinate updates and backtracking line searches.
title Optimal First-Order Algorithms as a Function of Inequalities
topic Optimization and Control
url https://arxiv.org/abs/2110.11035