Best-arm identification (BAI) aims to identify the optimal arm using as few samples as possible. While most existing work focuses on a single objective, many real-world applications involve multiple criteria, which motivates the study of BAI in multi-objective bandits. Intuitively, multi-objective identification seems harder, since the learner must identify optimal arms in a higher-dimensional reward space; however, the additional objectives also provide richer feedback that can reduce the required exploration. In this paper, we characterize when and why multiple objectives can make BAI easier. For Gaussian bandits, we establish a characteristic-time lower bound for fixed-confidence identification that holds uniformly across preference orders. Through explicit comparisons under Pareto, linear, and lexicographic preferences, we reveal three phenomena: (i) identifying a larger optimal set can require fewer samples than identifying a unique optimum; (ii) the advantage of vector feedback over coordinate feedback depends fundamentally on the preference order; and (iii) multi-objective identification can require fewer samples than even the easiest corresponding single-objective problem. Finally, we propose Order-Aware Track-and-Stop (OATS), an algorithm that is correct at any prescribed confidence level and asymptotically matches the lower bound.
National University of Singapore（新加坡国立大学）；Massachusetts Institute of Technology（麻省理工学院）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究院）
Modelling of Bi-directional Spatio-Temporal Dependence and Users' Dynamic Preferences for Missing POI Check-in Identification
University of Chinese Academy of Sciences（中国科学院大学）；Management Science & Information Systems, Rutgers University（罗格斯大学管理科学与信息系统系）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Business Intelligence Lab, Baidu Inc.（百度公司商业智能实验室）
Active Preference Learning over Latent Preference Archetypes for Many-Objective Bayesian Optimization
University of Manchester（曼彻斯特大学）；University of Edinburgh（爱丁堡大学）；Aalto University（阿尔托大学）；University of Amsterdam（阿姆斯特丹大学）；ELLIS Institute Finland（芬兰ELLIS研究所）
Exploiting Bi-directional Global Transition Patterns and Personal Preferences for Missing POI Category Identification
Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS（中国科学院智能信息处理重点实验室，中国科学院计算技术研究所）；Meituan-Dianping Group（美团点评集团）；Xiamen Data Intelligence Academy of ICT, CAS（中国科学院计算技术研究所厦门数据智能研究院）；Rutgers University（罗格斯大学）；Baidu Inc.（百度公司）；Soochow University（苏州大学）；iFLYTEK（科大讯飞）；University of Chinese Academy of Sciences（中国科学院大学）
A Multi-Task Text Classification Pipeline with Natural Language Explanations: A User-Centric Evaluation in Sentiment Analysis and Offensive Language Identification in Greek Tweets
