Work

Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields

Year: 2022

Type: article

Abstract: Reconstructing force fields (FFs) from atomistic simulation data is a challenge since accurate data can be highly expensive. Here, machine learning (ML) models can help to be data economic as they can be successfully constrained using the underlying symmetry and conservation laws of physics. However, so far, every descriptor newly proposed for an ML model has required a cumbersome and mathematically tedious remodeling. We therefore propose using modern techniques from algorithmic differentiation within the ML modeling process, effectively enabling the usage of novel descriptors or models fully automatically at an order of magnitude higher computational efficiency. This paradigmatic approach enables not only a versatile usage of novel representations and the efficient computation of larger systems─all of high value to the FF community─but also the simple inclusion of further physical knowledge, such as higher-order information (e.g., Hessians, more complex partial differential equations constraints etc.), even beyond the presented FF domain.

Source: The Journal of Physical Chemistry Letters

DOI: 10.1021/acs.jpclett.2c02632

Authors: Niklas Frederik Schmitz, Klaus-Robert Müller, Stefan Chmiela

Institutions: Technische Universität Berlin, Google (United States), Korea University, Max Planck Institute for Informatics, Berlin Institute for the Foundations of Learning and Data

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $5,000

Funder: Bundesministerium für Bildung und Forschung