Towards Domain Adaptive Neural Contextual Bandits

📅 2024-06-13
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses domain adaptation in contextual bandits across heterogeneous domains—specifically, transferring policies from a source domain (e.g., animal experiments) to a target domain (e.g., human clinical trials) under distributional shift. We propose the first general framework for domain-adaptive contextual bandits, theoretically establishing a sublinear regret bound under cross-domain transfer—thereby relaxing the conventional single-domain assumption. Methodologically, we integrate neural representation learning with adversarial domain alignment to jointly optimize policy and domain-invariant features, leveraging labeled source data while respecting target-domain feedback constraints. Empirical evaluation on multiple real-world datasets demonstrates significant improvements over state-of-the-art contextual bandit methods, confirming strong cross-domain generalization and practical feasibility for clinical deployment.

Technology Category

Application Category

📝 Abstract
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.
Problem

Research questions and friction points this paper is trying to address.

Adapting contextual bandits across domains with distribution shift
Reducing feedback collection costs from different domains
Achieving sub-linear regret in cross-domain adaptation
Innovation

Methods, ideas, or system contributions that make the work stand out.

Domain adaptation for contextual bandits
Learns target model from source feedback
Sub-linear regret bound across domains
🔎 Similar Papers
No similar papers found.
Z
Ziyang Wang
Georgia Institute of Technology
H
Hao Wang
Rutgers University