The fast committor machine: Interpretable prediction with kernels

作者：David Aristoff, Mats Johnson, Gideon Simpson, Robert J. Webber · 发表于：The Journal of Chemical Physics · 年份：2024 · DOI：10.1063/5.0222798 · 被引用次数：7 · 研究领域：Neural Networks and Applications、Machine Learning in Materials Science、Model Reduction and Neural Networks

In the study of stochastic systems, the committor function describes the probability that a system starting from an initial configuration x will reach a set B before a set A. This paper introduces an efficient and interpretable algorithm for approximating the committor, called the "fast committor machine" (FCM). The FCM uses simulated trajectory data to build a kernel-based model of the committor. The kernel function is constructed to emphasize low-dimensional subspaces that optimally describe the A to B transitions. The coefficients in the kernel model are determined using randomized linear algebra, leading to a runtime that scales linearly with the number of data points. In numerical experiments involving a triple-well potential and alanine dipeptide, the FCM yields higher accuracy and trains more quickly than a neural network with the same number of parameters. The FCM is also more interpretable than the neural net.