Files and links (1)
SubmittedarXiv.org - Non-exclusive license to distribute, Open
Journal article
The fast committor machine: Interpretable prediction with kernels
The Journal of chemical physics, v 161(8)
28 Aug 2024
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
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.
Metrics
Details
- Title
- The fast committor machine: Interpretable prediction with kernels
- Creators
- David Aristoff - Colorado State UniversityMats Johnson - Colorado State UniversityGideon Simpson - Drexel UniversityRobert J. Webber - University of California San Diego
- Publication Details
- The Journal of chemical physics, v 161(8)
- Publisher
- AIP Publishing; MELVILLE
- Number of pages
- 11
- Grant note
- DMS 2111277 / National Science Foundation (https://doi.org/10.13039/100000001) N00014-18-1-2363 / Office of Naval Research (https://doi.org/10.13039/100000006) Carver Mead New Adventures Fund / Caltech Associates (https://doi.org/10.13039/100009676) FRG 1952777 / National Science Foundation (https://doi.org/10.13039/100000001)
- Resource Type
- Journal article
- Academic Unit
- Mathematics
- Web of Science ID
- WOS:001300369100002
- Scopus ID
- 2-s2.0-85202744936
- Other Identifier
- 991021900043704721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Chemistry, Physical
- Physics, Atomic, Molecular & Chemical