Split Gibbs Discrete Diffusion Posterior Sampling

2025-03-03 · Wenda Chu, Yang song, Yisong Yue

We study the problem of posterior sampling in discrete-state spaces using discrete diffusion models. While posterior sampling methods for continuous diffusion models have achieved remarkable progress, analogous methods for discrete diffusion models remain challenging. In this work, we introduce a principled plug-and-play discrete diffusion posterior sampling algorithm based on split Gibbs sampling, which we call SG-DPS. Our algorithm enables reward-guided generation and solving inverse problems in discrete-state spaces. We demonstrate that SG-DPS converges to the true posterior distribution on synthetic benchmarks, and enjoys state-of-the-art posterior sampling performance on a range of benchmarks for discrete data, achieving up to 2x improved performance compared to existing baselines.

📄 PDF Abstract BibTeX arXiv:2503.01161

Code (0)

등록된 구현이 없습니다.

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…

Test-Time Anchoring for Discrete Diffusion Posterior Sampling

2025-10-02 · Litu Rout, Andreas Lugmayr, Yasamin Jafarian, Srivatsan Varadharajan 외 arxiv

While continuous diffusion models have achieved remarkable success, discrete diffusion offers a unified framework for jointly modeling text and images. Beyond unification, discrete diffusion provides faster inference, fi…

Question Answering

Discrete Langevin-Inspired Posterior Sampling

2026-05-10 · Chaitanya Amballa, Sattwik Basu, Jorge Vančo Sampedro, Romit Roy Choudhury arxiv

We study posterior sampling for inverse problems in discrete state spaces using discrete diffusion models as generative priors. While continuous diffusion models have become widely used for inverse problems, their discre…

Image Restoration

From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models

2026-05-26 · Yuchen Liang, Ness Shroff, Yingbin Liang arxiv

Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, but, especially for uniform-rate models, they often require many steps to generate a single sample. Existing accele…

Music Generation

Plug-and-Play split Gibbs sampler: embedding deep generative priors in Bayesian inference

2023-04-21 · Florentin Coeurdoux, Nicolas Dobigeon, Pierre Chainais

This paper introduces a stochastic plug-and-play (PnP) sampling algorithm that leverages variable splitting to efficiently sample from a posterior distribution. The algorithm based on split Gibbs sampling (SGS) draws ins…

Bayesian Inference Denoising

Listening to the Noise: Blind Denoising with Gibbs Diffusion

2024-02-29 · David Heurtel-Depeiges, Charles C. Margossian, Ruben Ohana, Bruno Régaldo-Saint Blancard

In recent years, denoising problems have become intertwined with the development of deep generative models. In particular, diffusion models are trained like denoisers, and the distribution they model coincide with denois…

Bayesian Inference Denoising Diagnostic