Saved in:
Bibliographic Details
Main Authors: Cao, Linfeng, Shi, Ming, Shroff, Ness B.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.13457
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914159378038784
author Cao, Linfeng
Shi, Ming
Shroff, Ness B.
author_facet Cao, Linfeng
Shi, Ming
Shroff, Ness B.
contents Multi-objective multi-armed bandit (MO-MAB) problems traditionally aim to achieve Pareto optimality. However, real-world scenarios often involve users with varying preferences across objectives, resulting in a Pareto-optimal arm that may score high for one user but perform quite poorly for another. This highlights the need for customized learning, a factor often overlooked in prior research. To address this, we study a preference-aware MO-MAB framework in the presence of explicit user preference. It shifts the focus from achieving Pareto optimality to further optimizing within the Pareto front under preference-centric customization. To our knowledge, this is the first theoretical study of customized MO-MAB optimization with explicit user preferences. Motivated by practical applications, we explore two scenarios: unknown preference and hidden preference, each presenting unique challenges for algorithm design and analysis. At the core of our algorithms are preference estimation and preference-aware optimization mechanisms to adapt to user preferences effectively. We further develop novel analytical techniques to establish near-optimal regret of the proposed algorithms. Strong empirical performance confirm the effectiveness of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2502_13457
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Provably Efficient Multi-Objective Bandit Algorithms under Preference-Centric Customization
Cao, Linfeng
Shi, Ming
Shroff, Ness B.
Machine Learning
Multi-objective multi-armed bandit (MO-MAB) problems traditionally aim to achieve Pareto optimality. However, real-world scenarios often involve users with varying preferences across objectives, resulting in a Pareto-optimal arm that may score high for one user but perform quite poorly for another. This highlights the need for customized learning, a factor often overlooked in prior research. To address this, we study a preference-aware MO-MAB framework in the presence of explicit user preference. It shifts the focus from achieving Pareto optimality to further optimizing within the Pareto front under preference-centric customization. To our knowledge, this is the first theoretical study of customized MO-MAB optimization with explicit user preferences. Motivated by practical applications, we explore two scenarios: unknown preference and hidden preference, each presenting unique challenges for algorithm design and analysis. At the core of our algorithms are preference estimation and preference-aware optimization mechanisms to adapt to user preferences effectively. We further develop novel analytical techniques to establish near-optimal regret of the proposed algorithms. Strong empirical performance confirm the effectiveness of our approach.
title Provably Efficient Multi-Objective Bandit Algorithms under Preference-Centric Customization
topic Machine Learning
url https://arxiv.org/abs/2502.13457