Saved in:
Bibliographic Details
Main Authors: Wang, Ziyan, Huo, Xiaoming, Wang, Hao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.09564
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910904685166592
author Wang, Ziyan
Huo, Xiaoming
Wang, Hao
author_facet Wang, Ziyan
Huo, Xiaoming
Wang, Hao
contents Contextual bandit algorithms are essential for solving real-world decision making problems. In practice, collecting a contextual bandit's feedback from different domains may involve different costs. For example, measuring drug reaction from mice (as a source domain) and humans (as a target domain). Unfortunately, adapting a contextual bandit algorithm from a source domain to a target domain with distribution shift still remains a major challenge and largely unexplored. In this paper, we introduce the first general domain adaptation method for contextual bandits. Our approach learns a bandit model for the target domain by collecting feedback from the source domain. Our theoretical analysis shows that our algorithm maintains a sub-linear regret bound even adapting across domains. Empirical results show that our approach outperforms the state-of-the-art contextual bandit algorithms on real-world datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2406_09564
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Towards Domain Adaptive Neural Contextual Bandits
Wang, Ziyan
Huo, Xiaoming
Wang, Hao
Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
Computer Vision and Pattern Recognition
Contextual bandit algorithms are essential for solving real-world decision making problems. In practice, collecting a contextual bandit's feedback from different domains may involve different costs. For example, measuring drug reaction from mice (as a source domain) and humans (as a target domain). Unfortunately, adapting a contextual bandit algorithm from a source domain to a target domain with distribution shift still remains a major challenge and largely unexplored. In this paper, we introduce the first general domain adaptation method for contextual bandits. Our approach learns a bandit model for the target domain by collecting feedback from the source domain. Our theoretical analysis shows that our algorithm maintains a sub-linear regret bound even adapting across domains. Empirical results show that our approach outperforms the state-of-the-art contextual bandit algorithms on real-world datasets.
title Towards Domain Adaptive Neural Contextual Bandits
topic Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.09564