mlsanityData to 7 Oct 2026

Best Arm Identification with Resource Constraints

arXiv 2402.19090 ↗First posted 29 Feb 2024cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Motivated by the cost heterogeneity in experimentation across different alternatives, we study the Best Arm Identification with Resource Constraints (BAIwRC) problem. The agent aims to identify the best arm under resource constraints, where resources are consumed for each arm pull. We make two novel contributions. We design and analyze the Successive Halving with Resource Rationing algorithm (SH-RR). The SH-RR achieves a near-optimal non-asymptotic rate of convergence in terms of the probability of successively identifying an optimal arm. Interestingly, we identify a difference in convergence rates between the cases of deterministic and stochastic resource consumption.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 23 of its 55 references that are in the map. First posted on arXiv 29 Feb 2024.

Builds on

23 of 55 references.

References · 23

  1. 2018A Tutorial on Bayesian Optimizationcited by 734
  2. 2014On the Complexity of Best Arm Identification in Multi-Armed Bandit Modelscited by 280
  3. 2016Optimal Best Arm Identification with Fixed Confidencecited by 233
  4. 2015Non-stochastic Best Arm Identification and Hyperparameter Optimizationcited by 219
  5. 2018A System for Massively Parallel Hyperparameter Tuningcited by 201
  6. 2013Bandits with Knapsackscited by 163
  7. 2013lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Banditscited by 148
  8. 2017Multi-fidelity Bayesian Optimisation with Continuous Approximationscited by 120
  9. 2019Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuningcited by 91
  10. 2014Bandits with concave rewards and convex knapsackscited by 83
  11. 2016Multi-Information Source Optimizationcited by 83
  12. 2015Linear Contextual Bandits with Knapsackscited by 82
11 more
  1. 2016Tight (Lower) Bounds for the Fixed Budget Best Arm Identification Bandit Problemcited by 79
  2. 2018Stagewise Safe Bayesian Optimization with Gaussian Processescited by 79
  3. 2020Cost-aware Bayesian Optimizationcited by 41
  4. 2021Best Arm Identification with Safety Constraintscited by 25
  5. 2017Combinatorial Semi-Bandits with Knapsackscited by 23
  6. 2022Multi-Fidelity Cost-Aware Bayesian Optimizationcited by 20
  7. 2022Almost Optimal Variance-Constrained Best Arm Identificationcited by 16
  8. 2019Cost-aware Multi-objective Bayesian optimisationcited by 8
  9. 2022Bayesian Optimization Over Iterative Learners with Structured Responses: A Budget-aware Planning Approachcited by 8
  10. 2020Pareto-efficient Acquisition Functions for Cost-Aware Bayesian Optimizationcited by 5
  11. 2021A resource-efficient method for repeated HPO and NAS problemscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validationcited by 1
  2. 2025Deceptive Exploration in Multi-armed Banditscited by 1
  3. 2026Test-Time Scaling via Budgeted Multi-Attribute Verificationcited by 0