A theoretical case study of the generalization of machine-learned potentials

DOI10.1016/J.CMA.2024.116831arXiv2311.01664OpenAlexW4391831269MaRDI QIDQ6125490

Shashwat Patel, Yangshuai Wang, Christoph Ortner

Publication date: 11 April 2024

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2311.01664

zbMATH Keywords

error analysisdislocationscrystal defectsmodel generalizationmachine-learned potentials

Mathematics Subject Classification ID

Biology and other natural sciences (92-XX) Computer science (68-XX)

Cites Work

• Unnamed Item
• Analysis of blended atomistic/continuum hybrid methods
• Analysis of boundary conditions for crystal defect atomistic simulations
• A comprehensive framework for verification, validation, and uncertainty quantification in scientific computing
• Cauchy-Born rule and the stability of crystalline solids: Static problems
• Thermodynamic limit of crystal defects with finite temperature tight binding
• Justification of the Cauchy-Born approximation of elastodynamics
• Error analysis for physics-informed neural networks (PINNs) approximating Kolmogorov PDEs
• Atomic cluster expansion: completeness, efficiency and stability
• Atomistic/Continuum Blending with Ghost Force Correction
• QM/MM Methods for Crystalline Defects. Part 1: Locality of the Tight Binding Model
• A priori and a posteriori analysis of the quasinonlocal quasicontinuum method in 1D
• Point defects in tight binding models for insulators
• Electronic Structure Calculations for Solids and Molecules
• Construction and Sharp Consistency Estimates for Atomistic/Continuum Coupling Methods with General Interfaces: A Two-Dimensional Model Problem
• Locality of interatomic forces in tight binding models for insulators
• A Posteriori Error Estimates for Adaptive QM/MM Coupling Methods
• Estimates on the generalization error of physics-informed neural networks for approximating a class of inverse problems for PDEs
• A priori analysis of a higher-order nonlinear elasticity model for an atomistic chain with periodic boundary condition
• Numerical Methods for Electronic Structure Calculations of Materials
• Geometry equilibration of crystalline defects in quantum and atomistic descriptions
• Analysis of Stable Screw Dislocation Configurations in an Antiplane Lattice Model
• Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials
• Atomistic-to-continuum coupling
• QM/MM Methods for Crystalline Defects. Part 2: Consistent Energy and Force-Mixing
• A Framework for a Generalization Analysis of Machine-Learned Interatomic Potentials
• Efficient a posteriori error control of a concurrent multiscale method with sharp interface for crystalline defects
• QM/MM Methods for Crystalline Defects. Part 3: Machine-Learned MM Models
• Adaptive multigrid strategy for geometry optimization of large-scale three dimensional molecular mechanics

This page was built for publication: A theoretical case study of the generalization of machine-learned potentials