Flow Matching之后的路径梯度
Path Gradients after Flow Matching
AI总结：
针对已知目标能量的分子平衡采样，本文提出用路径梯度微调经Flow Matching初始化的CNF，在不增加模型、预算和采样的情况下将采样效率最高提升三倍并保留流结构。
摘要：
Boltzmann生成器已成为一种很有前景的机器学习工具，可利用Normalizing Flows和重要性加权从分子系统的平衡分布中生成样本。最近，Flow Matching帮助加速了Continuous Normalizing Flows（CNF），将其扩展到更复杂的分子系统，并最小化流积分轨迹的长度。我们在目标能量已知的设定下，研究使用路径梯度微调最初由Flow Matching训练的CNF所带来的收益。实验表明，这种混合方法使分子系统的采样效率最高提升至三倍，同时使用相同模型、相近计算预算，且无需额外采样。此外，通过测量微调期间流轨迹的长度，我们证明路径梯度在很大程度上保留了流已学习到的结构。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
