Persistently Trained, Diffusion-assisted Energy-based Models

2023/04/21 by Xinwei Zhang, Zhiqiang Tan, Zhang, Xinwei +3
Medicine · #Advanced Neuroimaging Techniques and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.2304.10707

openalex publication_date 2023/04/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Maximum likelihood (ML) learning for energy-based models (EBMs) is challenging, partly due to non-convergence of Markov chain Monte Carlo.Several variations of ML learning have been proposed, but existing methods all fail to achieve both post-training image generation and proper density estimation. We propose to introduce diffusion data and learn a joint EBM, called diffusion assisted-EBMs, through persistent training (i.e., using persistent contrastive divergence) with an enhanced sampling algorithm to properly sample from complex, multimodal distributions. We present results from a 2D illustrative experiment and image experiments and demonstrate that, for the first time for image data, persistently trained EBMs can \it simultaneously achieve long-run stability, post-training image generation, and superior out-of-distribution detection.

Related

• Learning Energy-Based Models by Diffusion Recovery Likelihood
• Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihood
• Training Energy-Based Models with Diffusion Contrastive Divergences
• Improving Adversarial Energy-Based Model via Diffusion Process
• Learning Energy-Based Prior Model with Diffusion-Amortized MCMC