用扩散模型分步升温采样，提升生成效率与质量。
Progressive Tempering Sampler with Diffusion
- 分阶段训练扩散模型，逐步降低温度生成样本。
- 新方法融合高温模型生成低温近似样本，再微调。
- 采样更高效、独立，适合需要高质量样本的场景。
近期研究致力于设计神经采样器以摊销从非归一化密度中采样的过程。然而，尽管进展显著，其在目标评估效率上仍不及最先进的并行退火（PT）方法。另一方面，与训练好的神经采样器不同，PT仅产生依赖样本，且每次需重新运行，计算成本高。为此，我们提出渐进式退火扩散采样器（PTSD），通过在不同温度下顺序训练扩散模型，利用PT优势改进神经采样器的训练。我们还引入一种新方法，将高温扩散模型组合生成低温度近似样本，并通过少量MCMC微调后用于训练下一阶段扩散模型。PTSD实现了跨温度层级的样本信息复用，同时生成充分混合、无相关性的样本。该方法显著提升了目标评估效率，优于基于扩散的神经采样器。
原文摘要 · Abstract (English)
Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fall short of the state-of-the-art MCMC approach, Parallel Tempering (PT), when it comes to the efficiency of target evaluations. On the other hand, unlike a well-trained neural sampler, PT yields only dependent samples and needs to be rerun -- at considerable computational cost -- whenever new samples are required. To address these weaknesses, we propose the Progressive Tempering Sampler with Diffusion (PTSD), which trains diffusion models sequentially across temperatures, leveraging the advantages of PT to improve the training of neural samplers. We also introduce a novel method to combine high-temperature diffusion models to generate approximate lower-temperature samples, which are minimally refined using MCMC and used to train the next diffusion model. PTSD enables efficient reuse of sample information across temperature levels while generating well-mixed, uncorrelated samples. Our method significantly improves target evaluation efficiency, outperforming diffusion-based neural samplers.
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。