51 citations · 228 across the 23 of their papers we have counts for
5 papers · 1 filter
Predicting Properties of Periodic Systems from Cluster Data: A Case Study of Liquid Water
Viktor Zaverkin, David Holzmüller, Robin Schuldt +1
The accuracy of the training data limits the accuracy of bulk properties from machine-learned potentials. For example, hybrid functionals or wave-function-based quantum chemical me…
Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
Viktor Zaverkin, David Holzmüller, Henrik Christiansen +5
Efficiently creating a concise but comprehensive data set for training machine-learned interatomic potentials (MLIPs) is an under-explored problem. Active learning, which uses bias…
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
Moritz Haas, David Holzmüller, Ulrike von Luxburg +1
The success of over-parameterized neural networks trained to near-zero training error has caused great interest in the phenomenon of benign overfitting, where estimators are statis…
Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation
David Holzmüller, Francis Bach
Sampling from Gibbs distributions and computing their log-partition function are fundamental tasks in statistics, machine learning, and statistical physics. While efficient algorit…
Transfer learning for chemically accurate interatomic neural network potentials
Viktor Zaverkin, David Holzmüller, Luca Bonfirraro +1
Developing machine learning-based interatomic potentials from ab-initio electronic structure methods remains a challenging task for computational chemistry and materials science. T…