Ratio divergence learning using target energy in restricted Boltzmann machines: Beyond Kullback-Leibler divergence learning
Open Access
- 7 October 2025
- journal article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 112 (4) , 045306
Abstract
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.Keywords
All Related Versions
Funding Information
- Japan Science and Technology Corporation (JPMJPF2221)
- Japan Society for the Promotion of Science (23H01095)
This publication has 29 references indexed in Scilit:
- Machine-learning-assisted Monte Carlo fails at sampling computationally hard problemsMachine Learning: Science and Technology, 2023
- Normalizing flows for atomic solidsMachine Learning: Science and Technology, 2022
- Variational neural annealingNature Machine Intelligence, 2021
- Restricted Boltzmann machines in quantum physicsNature Physics, 2019
- Collective variable discovery and enhanced sampling using autoencoders: Innovations in network architecture and error function designThe Journal of Chemical Physics, 2018
- Reweighted autoencoded variational Bayes for enhanced sampling (RAVE)The Journal of Chemical Physics, 2018
- Restricted Boltzmann machines for neuroimaging: An application in identifying intrinsic networksNeuroImage, 2014
- emcee: The MCMC HammerPublications of the Astronomical Society of the Pacific, 2013
- Some extensions of score matchingComputational Statistics & Data Analysis, 2007
- Monte Carlo Simulation in Statistical PhysicsComputers in Physics, 1993