Saved in:
Bibliographic Details
Main Authors: Xue, Bo, Wan, Yuanyu, Lu, Zhichao, Zhang, Qingfu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.05802
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917069289684992
author Xue, Bo
Wan, Yuanyu
Lu, Zhichao
Zhang, Qingfu
author_facet Xue, Bo
Wan, Yuanyu
Lu, Zhichao
Zhang, Qingfu
contents In multi-objective decision-making with hierarchical preferences, lexicographic bandits provide a natural framework for optimizing multiple objectives in a prioritized order. In this setting, a learner repeatedly selects arms and observes reward vectors, aiming to maximize the reward for the highest-priority objective, then the next, and so on. While previous studies have primarily focused on regret minimization, this work bridges the gap between \textit{regret minimization} and \textit{best arm identification} under lexicographic preferences. We propose two elimination-based algorithms to address this joint objective. The first algorithm eliminates suboptimal arms sequentially, layer by layer, in accordance with the objective priorities, and achieves sample complexity and regret bounds comparable to those of the best single-objective algorithms. The second algorithm simultaneously leverages reward information from all objectives in each round, effectively exploiting cross-objective dependencies. Remarkably, it outperforms the known lower bound for the single-objective bandit problem, highlighting the benefit of cross-objective information sharing in the multi-objective setting. Empirical results further validate their superior performance over baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05802
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits
Xue, Bo
Wan, Yuanyu
Lu, Zhichao
Zhang, Qingfu
Machine Learning
Artificial Intelligence
In multi-objective decision-making with hierarchical preferences, lexicographic bandits provide a natural framework for optimizing multiple objectives in a prioritized order. In this setting, a learner repeatedly selects arms and observes reward vectors, aiming to maximize the reward for the highest-priority objective, then the next, and so on. While previous studies have primarily focused on regret minimization, this work bridges the gap between \textit{regret minimization} and \textit{best arm identification} under lexicographic preferences. We propose two elimination-based algorithms to address this joint objective. The first algorithm eliminates suboptimal arms sequentially, layer by layer, in accordance with the objective priorities, and achieves sample complexity and regret bounds comparable to those of the best single-objective algorithms. The second algorithm simultaneously leverages reward information from all objectives in each round, effectively exploiting cross-objective dependencies. Remarkably, it outperforms the known lower bound for the single-objective bandit problem, highlighting the benefit of cross-objective information sharing in the multi-objective setting. Empirical results further validate their superior performance over baselines.
title Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.05802