用于粗粒化分子表示主动学习的条件归一化流
Conditional Normalizing Flows for Active Learning of Coarse-Grained Molecular Representations
AI总结：
本文提出以粗粒化空间为条件的归一化流，并结合主动学习粗粒化模拟来缓解模式崩溃、高效学习分子 Boltzmann 分布，在丙氨酸二肽上实现最高约216.2倍加速。
摘要：
高效采样分子系统的 Boltzmann 分布是一项长期挑战。近来，研究人员不再生成长时间的分子动力学模拟，而是采用 normalizing flows（归一化流）等生成式机器学习方法，在没有样本的情况下直接学习 Boltzmann 分布。然而，该方法容易受到模式崩溃影响，因此往往无法探索完整的构型空间。在本工作中，我们通过将问题划分为两个层级来应对这一挑战，即细粒度自由度和粗粒化自由度。以粗粒化空间为条件的归一化流在两个层级之间建立了概率联系。为探索构型空间，我们采用结合主动学习的粗粒化模拟，这使我们能够更新该流，并且仅在必要时进行全原子势能评估。以丙氨酸二肽为例，我们证明，与当前最先进机器学习方法 4.5 倍的加速相比，我们的方法相对分子动力学模拟获得了约 15.9 至 216.2 倍的加速。
英文摘要：
Efficient sampling of the Boltzmann distribution of molecular systems is a long-standing challenge. Recently, instead of generating long molecular dynamics simulations, generative machine learning methods such as normalizing flows have been used to learn the Boltzmann distribution directly, without samples. However, this approach is susceptible to mode collapse and thus often does not explore the full configurational space. In this work, we address this challenge by separating the problem into two levels, the fine-grained and coarse-grained degrees of freedom. A normalizing flow conditioned on the coarse-grained space yields a probabilistic connection between the two levels. To explore the configurational space, we employ coarse-grained simulations with active learning which allows us to update the flow and make all-atom potential energy evaluations only when necessary. Using alanine dipeptide as an example, we show that our methods obtain a speedup to molecular dynamics simulations of approximately 15.9 to 216.2 compared to the speedup of 4.5 of the current state-of-the-art machine learning approach.
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。
