The Library
Comment on "Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four body interactions"
Tools
Pozdnyakov, Sergey, Willatt, Michael John, Bartok-Partay, Albert, Ortner, Christoph, Csanyi, Gabor and Ceriotti, Michele (2022) Comment on "Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four body interactions". The Journal of Chemical Physics, 157 . 177101. doi:10.1063/5.0088404 ISSN 1089-7690.
Research output not available from this repository.
Request-a-Copy directly from author or use local Library Get it For Me service.
Official URL: https://doi.org/10.1063/5.0088404
Abstract
The "quasi-constant' SOAP and ACSF fingerprint manifolds recently discovered by Parsaeifard and Goedecker[J. Chem. Phys. 156, 034302 (2022)] are closely related to the degenerate pairs of configurations, that are a known shortcoming of all low-body-order atom-density correlation representations of molecular structures. Configurations that are rigorously singular -- that we demonstrate can only occur in finite, discrete sets, and not as a continuous manifolds -- determine the complete failure of machine-learning models built on this class of descriptors. The ``quasi-constant' manifolds, on the other hand, exhibit low but non-zero sensitivity to atomic displacements. As a consequence, for any such manifold, it is possible to optimize the model parameters and the training set to mitigate their impact on learning, even though this is often impractical and it is preferable to use descriptors that avoid both the exact singularities and the associated numerical instability.
Item Type: | Journal Article | ||||||||
---|---|---|---|---|---|---|---|---|---|
Divisions: | Faculty of Science, Engineering and Medicine > Science > Mathematics Faculty of Science, Engineering and Medicine > Science > Physics |
||||||||
SWORD Depositor: | Library Publications Router | ||||||||
Journal or Publication Title: | The Journal of Chemical Physics | ||||||||
Publisher: | AIP Publishing | ||||||||
ISSN: | 1089-7690 | ||||||||
Official Date: | 2 November 2022 | ||||||||
Dates: |
|
||||||||
Volume: | 157 | ||||||||
Article Number: | 177101 | ||||||||
DOI: | 10.1063/5.0088404 | ||||||||
Status: | Peer Reviewed | ||||||||
Publication Status: | Published | ||||||||
Re-use Statement: | ** From Crossref journal articles via Jisc Publications Router ** History: epub 07-10-2022; issued 07-10-2022. | ||||||||
Access rights to Published version: | Open Access (Creative Commons) | ||||||||
Description: | Free access |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |