We propose a novel sequential Monte Carlo (SMC) method for sampling from unnormalized target distributions based on a reverse denoising diffusion process. While recent diffusion-based samplers simulate the reverse diffusion using approximate score functions, they can suffer from accumulating errors due to time discretization and imperfect score estimation. In this work, we introduce a principled SMC framework that formalizes diffusion-based samplers as proposals while systematically correcting for their biases. The core idea is to construct informative intermediate target distributions that progressively steer the sampling trajectory toward the final target distribution. Although ideal intermediate targets are intractable, we develop exact approximations using quantities from the score estimation-based proposal, without requiring additional model training or inference overhead. The resulting sampler, termed Reverse Diffusion Sequential Monte Carlo, enables consistent sampling and unbiased estimation of the target's normalization constant under mild conditions. We demonstrate the effectiveness of our method on a range of synthetic targets and real-world Bayesian inference problems.

翻译：我们提出了一种基于反向去噪扩散过程的序列蒙特卡洛（SMC）新方法，用于从未归一化的目标分布中采样。尽管现有的基于扩散的采样器利用近似得分函数模拟反向扩散过程，但它们可能因时间离散化和不完美的得分估计而累积误差。本文中，我们引入了一种原理性的SMC框架，将基于扩散的采样器形式化为提议分布，并系统性地校正其偏差。核心思想是构建信息丰富的中间目标分布，逐步引导采样轨迹趋近最终目标分布。虽然理想的中间目标分布难以精确求解，但我们利用基于得分估计的提议分布中的量值，开发了精确的近似方法，无需额外的模型训练或推理开销。所提出的采样器——称为反向扩散序列蒙特卡洛——在温和条件下能够实现一致性采样，并对目标分布的归一化常数进行无偏估计。我们在多种合成目标分布和实际贝叶斯推断问题上验证了该方法的有效性。