112 citations · 215 across the 7 of their papers we have counts for
7 papers
chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulations
Paul Fuchs, Weilong Chen, Stephan Thaler +1
Machine learning potentials (MLPs) have advanced rapidly and show great promise to transform molecular dynamics (MD) simulations. However, most existing software tools are tied to…
JaxSGMC: Modular stochastic gradient MCMC in JAX
Stephan Thaler, Paul Fuchs, Ana Cukarska +1
We present JaxSGMC, an application-agnostic library for stochastic gradient Markov chain Monte Carlo (SG-MCMC) in JAX. SG-MCMC schemes are uncertainty quantification (UQ) methods t…
chemtrain: Learning Deep Potential Models via Automatic Differentiation and Statistical Physics
Paul Fuchs, Stephan Thaler, Sebastien Röcken +1
Neural Networks (NNs) are effective models for refining the accuracy of molecular dynamics, opening up new fields of application. Typically trained bottom-up, atomistic NN potentia…
Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls
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. However, when applied o…
Deep Coarse-grained Potentials via Relative Entropy Minimization
Stephan Thaler, Maximilian Stupp, Julija Zavadlav
Neural network (NN) potentials are a natural choice for coarse-grained (CG) models. Their many-body capacity allows highly accurate approximations of the potential of mean force, p…
Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
Stephan Thaler, Julija Zavadlav
In molecular dynamics (MD), neural network (NN) potentials trained bottom-up on quantum mechanical data have seen tremendous success recently. Top-down approaches that learn NN pot…
Sparse Identification of Truncation Errors
Stephan Thaler, Ludger Paehler, Nikolaus A. Adams
This work presents a data-driven approach to the identification of spatial and temporal truncation errors for linear and nonlinear discretization schemes of Partial Differential Eq…