用神经网络高效模拟条件扩散路径，无需复杂采样。
Neural Guided Diffusion Bridges
- 用神经网络逼近扩散桥动态，替代传统采样方法
- 在稀有事件和多模态分布下表现更稳定
- 训练后采样效率接近无条件过程，适合实际应用
我们提出一种在欧氏空间中模拟条件扩散过程（扩散桥）的新方法。通过训练神经网络近似桥接动态，该方法避免了计算成本高昂的马尔可夫链蒙特卡洛（MCMC）或得分建模。相比现有方法，它在多种扩散设定和条件场景下更具鲁棒性，尤其适用于稀有事件和多模态分布，这些情况对基于得分学习和MCMC的方法构成挑战。我们引入一个由神经网络部分定义的灵活变分族，用于近似扩散桥路径测度。一旦训练完成，即可以与无条件（前向）过程采样相当的成本，高效生成独立的桥接路径。
原文摘要 · Abstract (English)
We propose a novel method for simulating conditioned diffusion processes (diffusion bridges) in Euclidean spaces. By training a neural network to approximate bridge dynamics, our approach eliminates the need for computationally intensive Markov Chain Monte Carlo (MCMC) methods or score modeling. Compared to existing methods, it offers greater robustness across various diffusion specifications and conditioning scenarios. This applies in particular to rare events and multimodal distributions, which pose challenges for score-learning- and MCMC-based approaches. We introduce a flexible variational family, partially specified by a neural network, for approximating the diffusion bridge path measure. Once trained, it enables efficient sampling of independent bridges at a cost comparable to sampling the unconditioned (forward) process.
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。