BOHB: Robust and Efficient Hyperparameter Optimization at Scale

By Stefan Falkner et al

Published on June 10, 2018

Read the original document by opening this link in a new tab.

Table of Contents

1. Introduction
2. Related Work on Model-based Hyperparameter Optimization
3. Bayesian Optimization and Hyperband
4. Model-Based Hyperband

Summary

Modern deep learning methods are very sensitive to many hyperparameters, and, due to the long training times of state-of-the-art models, vanilla Bayesian hyperparameter optimization is typically computationally infeasible. On the other hand, bandit-based configuration evaluation approaches based on random search lack guidance and do not converge to the best configurations as quickly. Here, we propose to combine the benefits of both Bayesian optimization and bandit-based methods, in order to achieve the best of both worlds: strong anytime performance and fast convergence to optimal configurations. Our method consistently outperforms both Bayesian optimization and Hyperband on a wide range of problem types, including high-dimensional toy functions, support vector machines, feed-forward neural networks, Bayesian neural networks, deep reinforcement learning, and convolutional neural networks. Our method is robust and versatile, while at the same time being conceptually simple and easy to implement.