Saved in:
Bibliographic Details
Main Authors: Hutchinson, Spencer, Turan, Berkay, Alizadeh, Mahnoosh
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2308.15006
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910363455324160
author Hutchinson, Spencer
Turan, Berkay
Alizadeh, Mahnoosh
author_facet Hutchinson, Spencer
Turan, Berkay
Alizadeh, Mahnoosh
contents The safe linear bandit problem is a version of the classical stochastic linear bandit problem where the learner's actions must satisfy an uncertain constraint at all rounds. Due its applicability to many real-world settings, this problem has received considerable attention in recent years. By leveraging a novel approach that we call directional optimism, we find that it is possible to achieve improved regret guarantees for both well-separated problem instances and action sets that are finite star convex sets. Furthermore, we propose a novel algorithm for this setting that improves on existing algorithms in terms of empirical performance, while enjoying matching regret guarantees. Lastly, we introduce a generalization of the safe linear bandit setting where the constraints are convex and adapt our algorithms and analyses to this setting by leveraging a novel convex-analysis based approach.
format Preprint
id arxiv_https___arxiv_org_abs_2308_15006
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Directional Optimism for Safe Linear Bandits
Hutchinson, Spencer
Turan, Berkay
Alizadeh, Mahnoosh
Machine Learning
The safe linear bandit problem is a version of the classical stochastic linear bandit problem where the learner's actions must satisfy an uncertain constraint at all rounds. Due its applicability to many real-world settings, this problem has received considerable attention in recent years. By leveraging a novel approach that we call directional optimism, we find that it is possible to achieve improved regret guarantees for both well-separated problem instances and action sets that are finite star convex sets. Furthermore, we propose a novel algorithm for this setting that improves on existing algorithms in terms of empirical performance, while enjoying matching regret guarantees. Lastly, we introduce a generalization of the safe linear bandit setting where the constraints are convex and adapt our algorithms and analyses to this setting by leveraging a novel convex-analysis based approach.
title Directional Optimism for Safe Linear Bandits
topic Machine Learning
url https://arxiv.org/abs/2308.15006