Denoising Diffusion Samplers

2023-02-27 · Francisco Vargas, Will Grathwohl, Arnaud Doucet

Denoising diffusion models are a popular class of generative models providing state-of-the-art results in many domains. One adds gradually noise to data using a diffusion to transform the data distribution into a Gaussian distribution. Samples from the generative model are then obtained by simulating an approximation of the time-reversal of this diffusion initialized by Gaussian samples. Practically, the intractable score terms appearing in the time-reversed process are approximated using score matching techniques. We explore here a similar idea to sample approximately from unnormalized probability density functions and estimate their normalizing constants. We consider a process where the target density diffuses towards a Gaussian. Denoising Diffusion Samplers (DDS) are obtained by approximating the corresponding time-reversal. While score matching is not applicable in this context, we can leverage many of the ideas introduced in generative modeling for Monte Carlo sampling. Existing theoretical results from denoising diffusion models also provide theoretical guarantees for DDS. We discuss the connections between DDS, optimal control and Schr\"odinger bridges and finally demonstrate DDS experimentally on a variety of challenging sampling tasks.

📄 PDF Abstract BibTeX arXiv:2302.13834

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

It Takes Two to Tango: Two Parallel Samplers Improve Quality in Diffusion Models for Limited Steps

2025-10-20 · Pedro Cisneros-Velarde arxiv

We consider the situation where we have a limited number of denoising steps, i.e., of evaluations of a diffusion model. We show that two parallel processors or samplers under such limitation can improve the quality of th…

RaSS: Improving Denoising Diffusion Samplers with Reinforced Active Sampling Scheduler

2025-01-01 · CVPR 2025 1 · Xin Ding, Lei Yu, Xin Li, Zhijun Tu 외

Recent years have witnessed the great success of denoising diffusion samplers in improving the generative capability and sampling efficiency given a pre-trained diffusion model. However, most sampling schedulers in d…

Denoising Reinforcement Learning (RL)

Understanding Sampler Stochasticity in Training Diffusion Models for RLHF

2025-10-12 · Jiayuan Sheng, Hanyang Zhao, Haoxian Chen, David D. Yao 외 arxiv

Reinforcement Learning from Human Feedback (RLHF) is increasingly used to fine-tune diffusion models, but a key challenge arises from the mismatch between stochastic samplers used during training and deterministic sample…

Reinforcement Learning

Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplers

2023-03-06 · Sitan Chen, Giannis Daras, Alexandros G. Dimakis

We develop a framework for non-asymptotic analysis of deterministic samplers used for diffusion generative modeling. Several recent works have analyzed stochastic samplers using tools like Girsanov's theorem and a chain …