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

By Jiazhuo Wang, Jason Xu, Xuejun Wang. 2018

94 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Frank Hutter
2. Aaron Klein
3. Stefan Falkner
4. Abdallah Shami
5. Li Yang
6. Tong Yu
7. Hong Zhu
8. Xuanyi Dong

In Computational Theory and Mathematics

1. Aaron Klein
2. Stefan Falkner
3. Frank Hutter
4. Li Yang
5. Abdallah Shami
6. Tong Yu
7. Hong Zhu
8. Holger H. Hoos

Citations in the corpus

• BOHB: Robust and Efficient Hyperparameter Optimization at Scale (2018, methodology): “Concurrently to our work, two other groups (Bertrand et al., 2017; Wang et al., 2018) also attempted to combine Bayesian optimization with Hyperband.”
• Hyper-Parameter Optimization: A Review of Algorithms and Applications (2020, background): “Several approaches combining BO and HB have been proposed in recent years (Bertrand et al., 2017; Falkner et al., 2018; Wang et al., 2018), to solve the native problem with HB.”
• On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice (2020, background): “However, GS, RS, and Hyperband all have a major constraint in that they treat each hyper-parameter independently and do not consider hyper-parameter correlations [107].”