mlsanityData to 7 Oct 2026

Non-stochastic Best Arm Identification and Hyperparameter Optimization

arXiv 1502.07943 ↗First posted 27 Feb 2015cs.LG stat.MLcited by 219

Not on the map. Why?

Abstract (arXiv)

Motivated by the task of hyperparameter optimization, we introduce the non-stochastic best-arm identification problem. Within the multi-armed bandit literature, the cumulative regret objective enjoys algorithms and analyses for both the non-stochastic and stochastic settings while to the best of our knowledge, the best-arm identification framework has only been considered in the stochastic setting. We introduce the non-stochastic setting under this framework, identify a known algorithm that is well-suited for this setting, and analyze its behavior. Next, by leveraging the iterative nature of standard machine learning algorithms, we cast hyperparameter optimization as an instance of non-stochastic best-arm identification, and empirically evaluate our proposed algorithm on this task. Our empirical results show that, by allocating more resources to promising hyperparameter settings, we typically achieve comparable test accuracies an order of magnitude faster than baseline methods.

Key facts. Cited by 219 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Feb 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 41; 2023: 35; 2024: 31; 2025: 39; 2026: 37.

219 papers.

Sort:

By area:

  1. 2023Symbolic Discovery of Optimization Algorithmscited by 423
  2. 2022Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfercited by 272
  3. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  4. 2023FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learningcited by 146
  5. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 143
  6. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  7. 2021HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPOcited by 111
  8. 2021HyperMorph: Amortized Hyperparameter Learning for Image Registrationcited by 84
  9. 2022Efficient Methods for Natural Language Processing: A Surveycited by 78
  10. 2023Using Large Language Models for Hyperparameter Optimizationcited by 71
  11. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  12. 2021YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimizationcited by 61
38 more
  1. 2021On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learningcited by 59
  2. 2022AMLB: an AutoML Benchmarkcited by 55
  3. 2021Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategiescited by 52
  4. 2022Learning the Effect of Registration Hyperparameters with HyperMorphcited by 35
  5. 2023PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learningcited by 31
  6. 2022Learning Curves for Decision Making in Supervised Machine Learning: A Surveycited by 27
  7. 2025AutoPDL: Automatic Prompt Optimization for LLM Agentscited by 27
  8. 2021VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decompositioncited by 25
  9. 2021Towards Green Automated Machine Learning: Status Quo and Future Directionscited by 25
  10. 2022Generalizing Few-Shot NAS with Gradient Matchingcited by 25
  11. 2023FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysiscited by 23
  12. 2024Super Consistency of Neural Network Landscapes and Learning Rate Transfercited by 23
  13. 2021Automated Discovery of Adaptive Attacks on Adversarial Defensescited by 22
  14. 2021Multi-objective Asynchronous Successive Halvingcited by 22
  15. 2022AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuningcited by 22
  16. 2022Bayesian Generational Population-Based Trainingcited by 20
  17. 2021Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimizationcited by 19
  18. 2021Promoting Fairness through Hyperparameter Optimizationcited by 17
  19. 2023Scaling Laws for Hyperparameter Optimizationcited by 16
  20. 2023Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoMLcited by 16
  21. 2021Fast and Informative Model Selection using Learning Curve Cross-Validationcited by 15
  22. 2022Supervising the Multi-Fidelity Race of Hyperparameter Configurationscited by 15
  23. 2021AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Flycited by 14
  24. 2021FLoRA: Single-shot Hyper-parameter Optimization for Federated Learningcited by 14
  25. 2022Efficient Automated Deep Learning for Time Series Forecastingcited by 14
  26. 2022DeepCAVE: An Interactive Analysis Tool for Automated Machine Learningcited by 14
  27. 2021Automated Deep Learning: Neural Architecture Search Is Not the Endcited by 13
  28. 2022Hyper-Tune: Towards Efficient Hyper-parameter Tuning at Scalecited by 13
  29. 2022Fair and Green Hyperparameter Optimization via Multi-objective and Multiple Information Source Bayesian Optimizationcited by 13
  30. 2022Transfer Learning based Search Space Design for Hyperparameter Tuningcited by 13
  31. 2022PASHA: Efficient HPO and NAS with Progressive Resource Allocationcited by 13
  32. 2024Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithmscited by 13
  33. 2021Efficient and Generalizable Tuning Strategies for Stochastic Gradient MCMCcited by 11
  34. 2023Optimizing Hyperparameters with Conformal Quantile Regressioncited by 10
  35. 2021RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halvingcited by 9
  36. 2022Automated Reinforcement Learning: An Overviewcited by 9
  37. 2023A Lipschitz Bandits Approach for Continuous Hyperparameter Optimizationcited by 9
  38. 2024Hyperband-based Bayesian Optimization for Black-box Prompt Selectioncited by 9

50 most cited of 219 All 219 (JSON)