用路径梯度优化流匹配训练的分子生成模型，提升采样效率三倍。
Path Gradients after Flow Matching
- 结合流匹配与路径梯度，微调连续流模型。
- 在相同计算量下，采样效率最高提升3倍。
- 适合需要高效分子采样的研究者使用。
Boltzmann生成器已成为利用归一化流和重要性加权从分子系统的平衡分布中生成样本的有力工具。近期，流匹配加速了连续归一化流（CNFs）的训练，使其可扩展至更复杂的分子系统，并缩短了流积分轨迹长度。本文研究在已知目标能量情况下，使用路径梯度对流匹配初始训练的CNFs进行微调的收益。实验表明，该混合方法在保持相同模型架构、类似计算开销且无需额外采样条件下，使分子系统的采样效率最高提升三倍。此外，通过测量微调过程中流轨迹的长度，我们发现路径梯度基本保留了流的已学习结构。
原文摘要 · Abstract (English)
Boltzmann Generators have emerged as a promising machine learning tool for generating samples from equilibrium distributions of molecular systems using Normalizing Flows and importance weighting. Recently, Flow Matching has helped speed up Continuous Normalizing Flows (CNFs), scale them to more complex molecular systems, and minimize the length of the flow integration trajectories. We investigate the benefits of using path gradients to fine-tune CNFs initially trained by Flow Matching, in the setting where a target energy is known. Our experiments show that this hybrid approach yields up to a threefold increase in sampling efficiency for molecular systems, all while using the same model, a similar computational budget and without the need for additional sampling. Furthermore, by measuring the length of the flow trajectories during fine-tuning, we show that path gradients largely preserve the learned structure of the flow.
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。