arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.02080cs.LGstat.COstat.ML
收藏

基于能量的扩散生成器用于玻尔兹曼分布的高效采样

Energy based diffusion generator for efficient sampling of Boltzmann distributions

School of Mathematical Sciences, Tongji University(同济大学数学科学学院);Department of Mathematics, Shanghai Normal University(上海师范大学数学系);Institute of Computational Mathematics and Scientific/Engineering Computing, AMSS, Chinese Academy of Sciences(中国科学院数学与系统科学研究院)

Yan Wang, Ling Guo, Hao Wu, Tao Zhou

AI总结:

提出基于能量的扩散生成器(EDG),融合变分自编码器与扩散模型,实现无模拟的高效玻尔兹曼分布采样,在复杂目标分布任务上优于现有方法。

摘要:

从玻尔兹曼分布中采样,特别是与高维和复杂能量函数相关的分布,在许多领域构成了重大挑战。在这项工作中,我们提出了基于能量的扩散生成器(EDG),一种融合了变分自编码器和扩散模型思想的新方法。EDG使用解码器从简单的潜变量生成玻尔兹曼分布的样本,并使用基于扩散的编码器来估计与目标分布的Kullback-Leibler散度。值得注意的是,EDG是无模拟的,在训练过程中无需解常微分或随机微分方程。此外,通过去除解码器中的双射性等约束,EDG允许灵活的网络设计。通过实证评估,我们展示了EDG在各种具有复杂目标分布的采样任务中的优越性能,优于现有方法。

英文摘要:

Sampling from Boltzmann distributions, particularly those tied to high dimensional and complex energy functions, poses a significant challenge in many fields. In this work, we present the Energy-Based Diffusion Generator (EDG), a novel approach that integrates ideas from variational autoencoders and diffusion models. EDG uses a decoder to generate Boltzmann-distributed samples from simple latent variables, and a diffusion-based encoder to estimate the Kullback-Leibler divergence to the target distribution. Notably, EDG is simulation-free, eliminating the need to solve ordinary or stochastic differential equations during training. Furthermore, by removing constraints such as bijectivity in the decoder, EDG allows for flexible network design. Through empirical evaluation, we demonstrate the superior performance of EDG across a variety of sampling tasks with complex target distributions, outperforming existing methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑