Denoising diffusion models have become ubiquitous for generative modeling. The core idea is to transport the data distribution to a Gaussian by using a diffusion. Approximate samples from the data distribution are then obtained by estimating the time-reversal of this diffusion using score matching ideas. We follow here a similar strategy to sample from unnormalized probability densities and compute their normalizing constants. However, the time-reversed diffusion is here simulated by using an original iterative particle scheme relying on a novel score matching loss. Contrary to standard denoising diffusion models, the resulting Particle Denoising Diffusion Sampler (PDDS) provides asymptotically consistent estimates under mild assumptions. We demonstrate PDDS on multimodal and high dimensional sampling tasks.

翻译：去噪扩散模型已成为生成建模中无处不在的工具。其核心思想是通过扩散过程将数据分布转换为高斯分布。随后，通过基于分数匹配思想估计该扩散过程的时间反转，可获得数据分布的近似样本。本文采用类似策略，从非归一化概率密度中采样并计算其归一化常数。然而，此处的时间反转扩散通过一种依赖新型分数匹配损失的原创迭代粒子方案进行模拟。与标准去噪扩散模型不同，所得粒子去噪扩散采样器（PDDS）在温和假设下提供渐近一致的估计结果。我们在多模态与高维采样任务上验证了PDDS的性能。