提出新方法实现离散空间后验采样，解决基因序列设计等逆问题。
Split Gibbs Discrete Diffusion Posterior Sampling
- 基于分裂吉布斯采样设计可插拔的离散扩散后验采样算法
- 在DNA序列、离散图像修复和音乐补全任务上提升超30%性能
- 适用于需奖励引导生成的离散数据逆问题，代码开源
我们研究了在离散状态空间中使用离散扩散模型进行后验采样的问题。尽管连续扩散模型的后验采样已取得显著进展，但离散扩散模型的类似方法仍面临挑战。本文提出一种基于分裂吉布斯采样的原理性插件式离散扩散后验采样算法（SGDD），支持奖励引导生成和离散状态空间中的逆问题求解。我们证明了SGDD收敛至目标后验分布，并通过合成基准测试验证其有效性。在多种离散数据基准测试中，包括DNA序列设计、离散图像逆问题和音乐补全任务上，该方法达到当前最优性能，相比现有基线提升超过30%。代码已公开于https://github.com/chuwd19/Split-Gibbs-Discrete-Diffusion-Posterior-Sampling。
原文摘要 · Abstract (English)
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 SGDD. Our algorithm enables reward-guided generation and solving inverse problems in discrete-state spaces. We demonstrate the convergence of SGDD to the target posterior distribution and verify this through controlled experiments on synthetic benchmarks. Our method enjoys state-of-the-art posterior sampling performance on a range of benchmarks for discrete data, including DNA sequence design, discrete image inverse problems, and music infilling, achieving more than 30% improved performance compared to existing baselines. Our code is available at https://github.com/chuwd19/Split-Gibbs-Discrete-Diffusion-Posterior-Sampling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。