English

Non-stochastic Best Arm Identification and Hyperparameter Optimization

Machine Learning 2015-03-02 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1502.07943,
  title  = {Non-stochastic Best Arm Identification and Hyperparameter Optimization},
  author = {Kevin Jamieson and Ameet Talwalkar},
  journal= {arXiv preprint arXiv:1502.07943},
  year   = {2015}
}
R2 v1 2026-06-22T08:39:49.304Z