mlsanityData to 7 Oct 2026

Differential Good Arm Identification

arXiv 2303.07154 ↗First posted 13 Mar 2023cs.LG stat.MLcited by 8

Not on the map. Why?

Abstract (arXiv)

This paper targets a variant of the stochastic multi-armed bandit problem called good arm identification (GAI). GAI is a pure-exploration bandit problem with the goal to output as many good arms using as few samples as possible, where a good arm is defined as an arm whose expected reward is greater than a given threshold. In this work, we propose DGAI - a differentiable good arm identification algorithm to improve the sample complexity of the state-of-the-art HDoC algorithm in a data-driven fashion. We also showed that the DGAI can further boost the performance of a general multi-arm bandit (MAB) problem given a threshold as a prior knowledge to the arm set. Extensive experiments confirm that our algorithm outperform the baseline algorithms significantly in both synthetic and real world datasets for both GAI and MAB tasks.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 9 of its 32 references that are in the map. First posted on arXiv 13 Mar 2023.

Builds on

9 of 32 references.

References · 9

  1. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  2. 2019Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networkscited by 221
  3. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  4. 2016Simple Bayesian Algorithms for Best Arm Identificationcited by 116
  5. 2016An optimal algorithm for the Thresholding Bandit Problemcited by 62
  6. 2015Bootstrapped Thompson Sampling and Deep Explorationcited by 40
  7. 2018Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Banditscited by 33
  8. 2017Good Arm Identification via Bandit Feedbackcited by 29
  9. 2020Differentiable Linear Bandit Algorithmcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 1.

8 papers.

  1. 2024Code Less, Align More: Efficient LLM Fine-tuning for Code Generation with Data Pruningcited by 19
  2. 2024lil'HDoC: An Algorithm for Good Arm Identification under Small Threshold Gapcited by 5
  3. 2024Enhance the Robustness of Text-Centric Multimodal Alignmentscited by 4
  4. 2025Uncertainty Profiles for LLMs: Uncertainty Source Decomposition and Adaptive Model-Metric Selectioncited by 4
  5. 2024LinearAPT: An Adaptive Algorithm for the Fixed-Budget Thresholding Linear Bandit Problemcited by 2
  6. 2025Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validationcited by 1
  7. 2025Multimodal Chip Physical Design Engineer Assistantcited by 1
  8. 2026An Efficient Algorithm for Thresholding Monte Carlo Tree Searchcited by 0