Yuichi Ishida
Research Subjects
Yuichi Ishida has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Aki Dote
Fujitsu Ltd 4-1-1 Kamikodanaka Nakahara-ku 211-8588 Kawasaki Kanagawa Japan
1 shared publication - Koji Hukushima
The University of Tokyo
1 shared publication Toshiyuki Miyazawa
Fujitsu Ltd
1 shared publication- Yuma Ichikawa
Fujitsu Limited
1 shared publication
Latest Publications
- Open Access
- 7 October 2025
- Published by American Physical Society (APS) in Physical Review E
- Vol. 112 (4) , 045306
Ratio divergence learning using target energy in restricted Boltzmann machines: Beyond Kullback-Leibler divergence learning
We propose ratio divergence (RD) learning for discrete energy-based models, a method that utilizes both training data and a tractable target energy function. We apply RD learning to restricted Boltzmann machines (RBMs), which are a minimal model that satisfies the universal approximation theorem for discrete distributions. RD learning combines the strength of both forward and reverse Kullback–Leibler divergence (KLD) learning, effectively addressing the “notorious” issues of underfitting with the forward KLD and mode collapse with the reverse KLD. Since the summation of forward and reverse KLD seems to be sufficient to combine the strength of both approaches, we include this learning method as a direct baseline in numerical experiments to evaluate its effectiveness. Numerical experiments demonstrate that RD learning outperforms other learning methods in terms of energy function fitting, mode-covering, and learning stability across various discrete energy-based models. Moreover, the performance gaps between RD learning and the other learning methods become more pronounced as the dimensions of target models increase.
- 7 October 2025
- Published by American Physical Society (APS) in Physical Review E
- Vol. 112 (4) , 045306
Open AccessRatio divergence learning using target energy in restricted Boltzmann machines: Beyond Kullback-Leibler divergence learning
We propose ratio divergence (RD) learning for discrete energy-based models, a method that utilizes both training data and a tractable target energy function. We apply RD learning to restricted Boltzmann machines (RBMs), which are a minimal model that satisfies the universal approximation theorem for discrete distributions. RD learning combines the strength of both forward and reverse Kullback–Leibler divergence (KLD) learning, effectively addressing the “notorious” issues of underfitting with the forward KLD and mode collapse with the reverse KLD. Since the summation of forward and reverse KLD seems to be sufficient to combine the strength of both approaches, we include this learning method as a direct baseline in numerical experiments to evaluate its effectiveness. Numerical experiments demonstrate that RD learning outperforms other learning methods in terms of energy function fitting, mode-covering, and learning stability across various discrete energy-based models. Moreover, the performance gaps between RD learning and the other learning methods become more pronounced as the dimensions of target models increase.