R.I.P.
๐ป
Ghosted
Data Curation for Machine Learning Interatomic Potentials by Determinantal Point Processes
March 23, 2026 ยท Grace Period ยท ๐ ICLR AI4MAT Workshop (2025)
Authors
Joanna Zou, Youssef Marzouk
arXiv ID
2603.22160
Category
stat.AP
Cross-listed
cs.LG
Citations
0
Venue
ICLR AI4MAT Workshop (2025)
Abstract
The development of machine learning interatomic potentials faces a critical computational bottleneck with the generation and labeling of useful training datasets. We present a novel application of determinantal point processes (DPPs) to the task of selecting informative subsets of atomic configurations to label with reference energies and forces from costly quantum mechanical methods. Through experiments with hafnium oxide data, we show that DPPs are competitive with existing approaches to constructing compact but diverse training sets by utilizing kernels of molecular descriptors, leading to improved accuracy and robustness in machine learning representations of molecular systems. Our work identifies promising directions to employ DPPs for unsupervised training data curation with heterogeneous or multimodal data, or in online active learning schemes for iterative data augmentation during molecular dynamics simulation.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ stat.AP
R.I.P.
๐ป
Ghosted
Sequence-to-point learning with neural networks for nonintrusive load monitoring
R.I.P.
๐ป
Ghosted
Predictive Business Process Monitoring with LSTM Neural Networks
R.I.P.
๐ป
Ghosted
Forecasting: theory and practice
R.I.P.
๐ป
Ghosted
Accurate estimation of influenza epidemics using Google search data via ARGO
R.I.P.
๐ป
Ghosted