Combination of Hyperband and Bayesian Optimization for Hyperparameter Optimization in Deep Learning

TL;DR

This paper proposes a novel method combining Hyperband and Bayesian optimization to improve hyperparameter tuning efficiency and effectiveness in deep learning, addressing the limitations of each approach individually.

Contribution

The paper introduces a combined Hyperband and Bayesian optimization method that leverages historical data to find better hyperparameters more efficiently in deep learning.

Findings

The combined method outperforms Hyperband alone in hyperparameter tuning tasks.

Experimental results demonstrate improved model performance and reduced tuning time.

The approach effectively utilizes past hyperparameter information for better sampling.

Abstract

Deep learning has achieved impressive results on many problems. However, it requires high degree of expertise or a lot of experience to tune well the hyperparameters, and such manual tuning process is likely to be biased. Moreover, it is not practical to try out as many different hyperparameter configurations in deep learning as in other machine learning scenarios, because evaluating each single hyperparameter configuration in deep learning would mean training a deep neural network, which usually takes quite long time. Hyperband algorithm achieves state-of-the-art performance on various hyperparameter optimization problems in the field of deep learning. However, Hyperband algorithm does not utilize history information of previous explored hyperparameter configurations, thus the solution found is suboptimal. We propose to combine Hyperband algorithm with Bayesian optimization (which does not ignore history when sampling next trial configuration). Experimental results show that our combination approach is superior to other hyperparameter optimization approaches including Hyperband algorithm.