MLDIS-NNLGSTMESep 12, 2024

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

arXiv:2409.07679v11 citationsh-index: 5
Originality Incremental advance
AI Analysis

This addresses a key bottleneck in training discrete energy-based models for machine learning applications, offering a more stable and effective method, though it appears incremental as it builds on existing divergence concepts.

The authors tackled the problem of underfitting and mode-collapse in discrete energy-based models like restricted Boltzmann machines by proposing ratio divergence learning, which uses a target energy function to combine forward and reverse Kullback-Leibler divergences, resulting in significant improvements in energy fitting, mode-covering, and stability, with performance gaps increasing with model dimensions.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes