Hideaki Ishibashi — accepted AI-conference papers

2023

A stopping criterion for Bayesian optimization by the gap of expected minimum simple regrets

Hideaki Ishibashi, Masayuki Karasuyama, Ichiro Takeuchi, Hideitsu Hino

AISTATS 2023poster

Bayesian optimization (BO) improves the efficiency of black-box optimization; however, the associated computational cost and power consumption remain dominant in the application of machine learning methods. This paper proposes a method of determining the stopping time in BO. The proposed criterion i…

Cited by 16 Source ↗PDF ↗Scholar ↗

2020

Stopping criterion for active learning based on deterministic generalization bounds

Hideaki Ishibashi, Hideitsu Hino

AISTATS 2020poster

Active learning is a framework in which the learning machine can select the samples to be used for training. This technique is promising, particularly when the cost of data acquisition and labeling is high. In active learning, determining the timing at which learning should be stopped is a critical…

Cited by 35 Source ↗PDF ↗Scholar ↗