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

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.

preprint

References in corpus (2)

• Convolutional neural networks with low-rank regularization
• Making a Science of Model Search

Cited by in corpus (8)

• On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice
• Hyper-Parameter Optimization: A Review of Algorithms and Applications
• BOHB: Robust and Efficient Hyperparameter Optimization at Scale
• An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization
• Enhancing network forensics with particle swarm and deep learning: The particle deep framework
• Weighting Is Worth the Wait: Bayesian Optimization with Importance Sampling
• Hyperparameter Optimization in Neural Networks via Structured Sparse Recovery
• Reducing The Search Space For Hyperparameter Optimization Using Group Sparsity