Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based Models
Yang Zitao, Amin Ullah, Shuai Li, Li Fuxin, Jun Li
Abstract
This paper introduces the Convex Potential Mirror Langevin Algorithm (CPMLA), a novel method to improve sampling efficiency for Energy-Based Models (EBMs). CPMLA uses mirror Langevin dynamics with a convex potential flow as a dynamic mirror map for EBM sampling. This dynamic mirror map enables targeted geometric exploration on the data manifold, accelerating convergence to the target distribution. Theoretical analysis proves that CPMLA achieves exponential convergence with vanishing bias under relaxed log-concave conditions, supporting its efficiency in adapting to complex data distributions. Experiments on benchmarks like CIFAR-10, SVHN, and CelebA demonstrate CPMLA's improved sampling quality and inference efficiency over existing techniques.
BibTeX
@inproceedings{
zitao2025convex,
title={Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based Models},
author={Yang Zitao and Amin Ullah and Shuai Li and Li Fuxin and Jun Li},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=KWFnxtO78b}
}