Particle Denoising Diffusion Sampler

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.

去噪扩散模型（Denoising Diffusion Models）已在生成建模领域得到广泛应用。其核心思想为通过扩散过程将数据分布迁移至高斯分布；随后借助得分匹配（score matching）的思想，通过估计该扩散过程的时间逆过程，即可获得数据分布的近似采样结果。