Saved in:
Bibliographic Details
Main Authors: Jacobsen, Andrew, Cutkosky, Ashok
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2203.00444
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916118596157440
author Jacobsen, Andrew
Cutkosky, Ashok
author_facet Jacobsen, Andrew
Cutkosky, Ashok
contents We develop a modified online mirror descent framework that is suitable for building adaptive and parameter-free algorithms in unbounded domains. We leverage this technique to develop the first unconstrained online linear optimization algorithm achieving an optimal dynamic regret bound, and we further demonstrate that natural strategies based on Follow-the-Regularized-Leader are unable to achieve similar results. We also apply our mirror descent framework to build new parameter-free implicit updates, as well as a simplified and improved unconstrained scale-free algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2203_00444
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Parameter-free Mirror Descent
Jacobsen, Andrew
Cutkosky, Ashok
Machine Learning
Optimization and Control
We develop a modified online mirror descent framework that is suitable for building adaptive and parameter-free algorithms in unbounded domains. We leverage this technique to develop the first unconstrained online linear optimization algorithm achieving an optimal dynamic regret bound, and we further demonstrate that natural strategies based on Follow-the-Regularized-Leader are unable to achieve similar results. We also apply our mirror descent framework to build new parameter-free implicit updates, as well as a simplified and improved unconstrained scale-free algorithm.
title Parameter-free Mirror Descent
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2203.00444