DeepAI AI Chat
Log In Sign Up

An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization

by   Yimin Huang, et al.
HUAWEI Technologies Co., Ltd.
Peking University

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).


page 1

page 2

page 3

page 4


Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search

While existing work on neural architecture search (NAS) tunes hyperparam...

Reducing The Search Space For Hyperparameter Optimization Using Group Sparsity

We propose a new algorithm for hyperparameter selection in machine learn...

L^2NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning

Neural architecture search (NAS) has achieved remarkable results in deep...

Hyperparameter Optimization in Neural Networks via Structured Sparse Recovery

In this paper, we study two important problems in the automated design o...

Hypernetwork-Based Augmentation

Data augmentation is an effective technique to improve the generalizatio...

Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL

Despite a series of recent successes in reinforcement learning (RL), man...

A Lipschitz Bandits Approach for Continuous Hyperparameter Optimization

One of the most critical problems in machine learning is HyperParameter ...