<ul><li>Energy-based models (EBMs) are a powerful class of probabilistic generative models.</li><li>Variational Potential Flow Bayes (VPFB) is a new energy-based generative framework that eliminates the need for implicit MCMC sampling.</li><li>VPFB learns an energy-parameterized potential flow by matching a flow-driven density homotopy to the data distribution.</li><li>Experimental results show that VPFB performs competitively with existing approaches in terms of sample quality and versatility.</li></ul>

Learning Energy-Based Generative Models via Potential Flow: A Variational Principle Approach to Probability Density Homotopy Matching

Discover more