Papers › Persistently Trained, Diffusion-assisted Energy-based Models

Persistently Trained, Diffusion-assisted Energy-based Models

21 Apr 2023arXiv:2304.10707archive 2025-07-28

Xinwei Zhang, Zhiqiang Tan, Zhijian Ou

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.

PaperPDFCode

Code

xinweizhang/daebm officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Density EstimationImage GenerationOut-of-Distribution Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionEBMfail

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections