English
Related papers

Related papers: Accelerating Training of MLIPs Through Small-Cell …

200 papers

Machine-learned interatomic potentials (MLIPs) are increasingly used to replace computationally demanding electronic-structure calculations to model matter at the atomic scale. The most commonly used model architectures are constrained to…

Chemical Physics · Physics 2026-03-30 Filippo Bigi , Paolo Pegolo , Arslan Mazitov , Jonathan Schmidt , Michele Ceriotti

Machine learning interatomic potentials (MLIPs) have become increasingly effective at approximating quantum mechanical calculations at a fraction of the computational cost. However, lower errors on held out test sets do not always translate…

Computational Physics · Physics 2025-04-24 Xiang Fu , Brandon M. Wood , Luis Barroso-Luque , Daniel S. Levine , Meng Gao , Misko Dzamba , C. Lawrence Zitnick

The ability to train ever-larger neural networks brings artificial intelligence to the forefront of scientific and technical discoveries. However, their exponentially increasing size creates a proportionally greater demand for energy and…

Accurate simulations of molecules require high-level electronic-structure theory in combination with rigorous methods for approximating the quantum dynamics. Machine-learning approaches can significantly reduce the computational expense of…

Chemical Physics · Physics 2026-02-24 Valerii Andreichev , Jindra Dušek , Markus Meuwly , Jeremy O. Richardson

We propose a data-driven approach for constructing machine-learning interatomic potentials (MLIPs) trained under a regularization with the aim of avoiding nonphysical heat flux. Specifically, we introduce a regularization term for the heat…

Computational Physics · Physics 2024-03-22 Kohei Shimamura , Koura Akihide , Fuyuki Shimojo

The promise of machine learning interatomic potentials (MLIPs) has led to an abundance of public quantum mechanical (QM) training datasets. The quality of an MLIP is directly limited by the accuracy of the energies and atomic forces in the…

Over the past decade inter-atomic potentials based on machine-learning (ML) techniques have become an indispensable tool in the atomic-scale modeling of materials. Trained on energies and forces obtained from electronic-structure…

Materials Science · Physics 2022-08-15 Michele Ceriotti

The use of machine learning interatomic potentials (MLIPs) in simulations of materials is a state-of-the-art approach, which allows achieving nearly \textit{ab initio} accuracy with orders of magnitude less computational cost.…

Materials Science · Physics 2021-10-28 R. E. Ryltsev , N. M. Chtchelkatchev

Quantum chemical simulations can be greatly accelerated by constructing machine learning potentials, which is often done using active learning (AL). The usefulness of the constructed potentials is often limited by the high effort required…

Chemical Physics · Physics 2024-09-19 Yi-Fan Hou , Lina Zhang , Quanhao Zhang , Fuchun Ge , Pavlo O. Dral

Solidification governs the microstructure and, therefore, the mechanical response of metal components, yet the atomistic details of nucleation and defect formation are often difficult to determine experimentally. Molecular dynamics can…

Computational Physics · Physics 2026-03-26 Ian Störmer , Julija Zavadlav

The ability to accurately model interatomic interactions in large-scale systems is fundamental to understanding a wide range of physical and chemical phenomena, from drug-protein binding to the behavior of next-generation materials. While…

Materials Science · Physics 2025-05-26 Taskin Mehereen , Sourav Saha , Intesar Jawad Jaigirdar , Chanwook Park

In this work, we propose several online methods to build a \emph{learning curriculum} from a given set of target-task-specific training tasks in order to speed up reinforcement learning (RL). These methods can decrease the total training…

Machine Learning · Computer Science 2017-11-22 Vikas Jain , Theja Tulabandhula

The length and time scales of atomistic simulations are limited by the computational cost of the methods used to predict material properties. In recent years there has been great progress in the use of machine learning algorithms to develop…

Computational Physics · Physics 2022-11-03 Alberto Hernandez , Adarsh Balasubramanian , Fenglin Yuan , Simon Mason , Tim Mueller

Machine learning interatomic potentials (MLIPs) balance high accuracy and lower costs compared to density functional theory calculations, but their performance often depends on the size and diversity of training datasets. Large datasets…

Machine Learning · Computer Science 2025-11-14 Benjamin Yu , Vincenzo Lordi , Daniel Schwalbe-Koda

One of the ultimate goals of computational modeling in condensed matter is to be able to accurately compute materials properties with minimal empirical information. First-principles approaches such as the density functional theory (DFT)…

Neural network potentials (NNPs) offer a powerful alternative to traditional force fields for molecular dynamics (MD) simulations. Accurate and stable MD simulations, crucial for evaluating material properties, require training data…

Machine Learning · Computer Science 2025-06-23 Naoki Matsumura , Yuta Yoshimoto , Yuto Iwasaki , Meguru Yamazaki , Yasufumi Sakai

Scaling transformers has led to significant breakthroughs in many domains, leading to a paradigm in which larger versions of existing models are trained and released on a periodic basis. New instances of such models are typically trained…

Molecular dynamics (MD) employing machine-learned interatomic potentials (MLIPs) serve as an efficient, urgently needed complement to ab initio molecular dynamics (aiMD). By training these potentials on data generated from ab initio…

Materials Science · Physics 2024-09-19 Kisung Kang , Thomas A. R. Purcell , Christian Carbogno , Matthias Scheffler

Machine-Learned Interatomic Potentials (MLIPs) require vast amounts of atomic structure data to learn forces and energies, and their performance continues to improve with training set size. Meanwhile, the even greater quantities of…

Chemical Physics · Physics 2025-12-09 Manasa Kaniselvan , Benjamin Kurt Miller , Meng Gao , Juno Nam , Daniel S. Levine

Machine-learning potentials (MLPs) for atomistic simulations are a promising alternative to conventional classical potentials. Current approaches rely on descriptors of the local atomic environment with dimensions that increase…

Materials Science · Physics 2017-12-05 Nongnuch Artrith , Alexander Urban , Gerbrand Ceder
‹ Prev 1 3 4 5 6 7 10 Next ›