An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization
Abstract
The evaluation of hyperparameters, neural architectures, or data augmentation policies becomes a critical model selection problem in advanced deep learning with a large hyperparameter search space. In this paper, we propose an efficient and robust bandit-based algorithm called Sub-Sampling (SS) in the scenario of hyperparameter search evaluation. It evaluates the potential of hyperparameters by the sub-samples of observations and is theoretically proved to be optimal under the criterion of cumulative regret. We further combine SS with Bayesian Optimization and develop a novel hyperparameter optimization algorithm called BOSS. Empirical studies validate our theoretical arguments of SS and demonstrate the superior performance of BOSS on a number of applications, including Neural Architecture Search (NAS), Data Augmentation (DA), Object Detection (OD), and Reinforcement Learning (RL).
Cite
@article{arxiv.2007.05670,
title = {An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization},
author = {Yimin Huang and Yujun Li and Hanrong Ye and Zhenguo Li and Zhihua Zhang},
journal= {arXiv preprint arXiv:2007.05670},
year = {2020}
}