Non-stochastic Best Arm Identification and Hyperparameter Optimization
From MaRDI portal
Publication:72742
DOI10.48550/ARXIV.1502.07943arXiv1502.07943MaRDI QIDQ72742FDOQ72742
Authors: Kevin Jamieson, Ameet Talwalkar 
Publication date: 27 February 2015
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.
Cited In (1)
This page was built for publication: Non-stochastic Best Arm Identification and Hyperparameter Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q72742)
