mlsanityData to 7 Oct 2026

Sequential Learning of the Pareto Front for Multi-objective Bandits

arXiv 2501.17513 ↗First posted 29 Jan 2025stat.ML cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

We study the problem of sequential learning of the Pareto front in multi-objective multi-armed bandits. An agent is faced with K possible arms to pull. At each turn she picks one, and receives a vector-valued reward. When she thinks she has enough information to identify the Pareto front of the different arm means, she stops the game and gives an answer. We are interested in designing algorithms such that the answer given is correct with probability at least 1-δ. Our main contribution is an efficient implementation of an algorithm achieving the optimal sample complexity when the risk δ is small. With K arms in d dimensions p of which are in the Pareto set, the algorithm runs in time O(Kpd) per round.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 19 of its 42 references that are in the map. First posted on arXiv 29 Jan 2025.

Builds on

19 of 42 references.

References · 19

  1. 2016Optimal Best Arm Identification with Fixed Confidencecited by 233
  2. 2020Optimal Best-arm Identification in Linear Banditscited by 70
  3. 2019Non-Asymptotic Pure Exploration by Solving Gamescited by 62
  4. 2020Gamification of Pure Exploration for Linear Banditscited by 61
  5. 2019Adaptive Exploration in Linear Contextual Banditcited by 43
  6. 2017Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selectioncited by 28
  7. 2017Multi-objective Bandits: Optimizing the Generalized Gini Indexcited by 27
  8. 2020An Asymptotically Optimal Primal-Dual Incremental Algorithm for Contextual Linear Banditscited by 26
  9. 2020Adaptive Sampling for Best Policy Identification in Markov Decision Processescited by 20
  10. 2020Optimal Best-Arm Identification Methods for Tail-Risk Measurescited by 17
  11. 2021A/B/n Testing with Control in the Presence of Subpopulationscited by 17
  12. 2017Thresholding Bandit for Dose-ranging: The Impact of Monotonicitycited by 15
7 more
  1. 2023Adaptive Algorithms for Relaxed Pareto Set Identificationcited by 13
  2. 2019Optimal Best Markovian Arm Identification with Fixed Confidencecited by 12
  3. 2022Pareto Regret Analyses in Multi-objective Multi-armed Banditcited by 11
  4. 2016Maximin Action Identification: A New Bandit Framework for Gamescited by 7
  5. 2019MaxGap Bandit: Adaptive Algorithms for Approximate Rankingcited by 6
  6. 2017Adaptive Multiple-Arm Identificationcited by 4
  7. 2017Skyline Identification in Multi-Armed Banditscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 6.

13 papers.

Sort:

  1. 2025Best Group Identification in Multi-Objective Banditscited by 2
  2. 2025Constrained Pareto Set Identification with Bandit Feedbackcited by 2
  3. 2025FraPPE: Fast and Efficient Preference-based Pure Explorationcited by 2
  4. 2025Multi-thresholding Good Arm Identification with Bandit Feedbackcited by 1
  5. 2025Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validationcited by 1
  6. 2025Stochastic Multi-Objective Multi-Armed Bandits: Regret Definition and Algorithmcited by 1
  7. 2026Communication-Corruption Coupling and Verification in Cooperative Multi-Objective Banditscited by 1
  8. 2026Cost-Aware Multi-Objective Bandits: Theory and Application to Budgeted LLM Configuration Evaluationcited by 1
  9. 2025Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Banditscited by 0
  10. 2026Probe-then-Commit Multi-Objective Bandits: Theoretical Benefits of Limited Multi-Arm Feedbackcited by 0
  11. 2026Bayesian Anytime Pareto Set Identification for Multi-Objective Multi-Armed Banditscited by 0
  12. 2026Selective Ensemble Based on Preference-Directed Multi-Objective Banditscited by 0
1 more
  1. 2026Efficient Online Lexicographic Generalized Low-Rank Matrix Banditscited by 0