提出新采样方法，提升扩散模型在强信息似然下的采样效率。
Generative diffusion posterior sampling for informative likelihoods
- 构建与扩散模型相关的观测路径，利用相关性提升采样效率。
- 在异常值和强信息似然条件下，统计效率显著优于现有方法。
- 适合需要高精度条件采样的研究者，如逆问题求解或罕见事件建模。
顺序蒙特卡洛（SMC）方法在生成式扩散模型的条件采样中取得了成功。本文提出一种新的扩散后验SMC采样器，在异常值情况或高度信息丰富的似然条件下实现了更高的统计效率。核心思想是构造一条与扩散模型相关联的观测路径，并设计采样器以利用该相关性实现更高效的采样。实验结果验证了该方法的高效性。
原文摘要 · Abstract (English)
Sequential Monte Carlo (SMC) methods have recently shown successful results for conditional sampling of generative diffusion models. In this paper we propose a new diffusion posterior SMC sampler achieving improved statistical efficiencies, particularly under outlier conditions or highly informative likelihoods. The key idea is to construct an observation path that correlates with the diffusion model and to design the sampler to leverage this correlation for more efficient sampling. Empirical results conclude the efficiency.
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。