Ratio Divergence Learning Using Target Energy in Restricted Boltzmann Machines: Beyond Kullback--Leibler Divergence Learning

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 significantly 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.

14 pages, 19 figures

References in corpus (10)

• emcee: The MCMC Hammer
• Exchange Monte Carlo Method and Application to Spin Glass Simulations
• Self-Learning Monte Carlo Method
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• Self-Learning Determinantal Quantum Monte Carlo Method
• Boosting Monte Carlo simulations of spin glasses using autoregressive neural networks
• Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems
• Convolutional restricted Boltzmann machine aided Monte Carlo: An application to Ising and Kitaev models
• Thermodynamics of the Ising model encoded in restricted Boltzmann machines