Generalized Contrastive Divergence: Joint Training of Energy-Based Model and Diffusion Model through Inverse Reinforcement Learning

no code implementations • 6 Dec 2023 • Sangwoong Yoon, Dohyun Kwon, Himchan Hwang, Yung-Kyun Noh, Frank C. Park

We present Generalized Contrastive Divergence (GCD), a novel objective function for training an energy-based model (EBM) and a sampler simultaneously.