[3J3-OS-3a] AutoML（自動機械学習）(1/2)

[3J3-OS-3a-02] Hyperparameter Optimization by Multi-objective Bayesian Optimization based on Inference of User Preference

〇Ryota Ozaki¹, Yusuke Takagi¹, Masayuki Karasuyama¹, Ichiro Takeuchi^1,2 (1. Nagoya Institute of Technology, 2. RIKEN Center for Advanced Intelligence Project)

Keywords:AutoML, Neural Network, Hyperparameter Optimization, Multi-objective Bayesian Optimization, Preference Learning

AutoML considers hyper-parameter optimization (HPO) of machine learning models. However, there often exist multiple evaluation indices for the learned models. For example, both model accuracy and memory size can be objective functions, which are typically in the trade-off relation. In this case, the importance of each objective function depends on the user preference. To incorporate the preference adaptively into HPO, we propose a preference-learning-based multi-objective Bayesian optimization (PL-MBO) method. Since directly specifying the exact preference can be difficult for the user, PL-MBO considers only querying a `relative preference’ that the user can give much easier. By combining a Bayesian user preference model and the standard Gaussian process model of objective functions, the expected improvement criterion of the user preference is derived. Our numerical experiments show that the optimal solution based on the user preference can be found efficiently in HPO for neural networks.