Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls

no code implementations • 15 Dec 2022 • Stephan Thaler, Gregor Doehner, Julija Zavadlav

Neural network (NN) potentials promise highly accurate molecular dynamics (MD) simulations within the computational complexity of classical MD force fields.

Decision Making Uncertainty Quantification

Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting

1 code implementation • 2 Jun 2021 • Stephan Thaler, Julija Zavadlav

In molecular dynamics (MD), neural network (NN) potentials trained bottom-up on quantum mechanical data have seen tremendous success recently.

Sparse Identification of Truncation Errors

1 code implementation • 7 Apr 2019 • Stephan Thaler, Ludger Paehler, Nikolaus A. Adams

We augment a sparse regression-rooted approach with appropriate preconditioning routines to aid in the identification of the individual modified differential equation terms.

Numerical Analysis 62J05, 65F08 (Primary) 90C31, 35Q35, 68W40 (Secondary) G.1.8; G.3; F.2.0