Related papers: Latent Ewald summation for machine learning of lon…
Deep Metric Learning (DML) approaches learn to represent inputs to a lower-dimensional latent space such that the distance between representations in this space corresponds with a predefined notion of similarity. This paper investigates how…
A proper treatment of electrostatic interactions is crucial for the accurate calculation of forces in computer simulations. Electrostatic interactions are typically modeled using Ewald based methods, which have become one of the…
Machine-learned interatomic potentials (MILPs) are rapidly gaining interest for molecular modeling, as they provide a balance between quantum-mechanical level descriptions of atomic interactions and reasonable computational efficiency.…
A core problem in machine learning is to learn expressive latent variables for model prediction on complex data that involves multiple sub-components in a flexible and interpretable fashion. Here, we develop an approach that improves…
Machine learning interatomic potentials (MLIPs) enables molecular dynamics (MD) simulations with ab initio accuracy and has been applied to various fields of physical science. However, the performance and transferability of MLIPs are…
Vibrational properties of solids are key to determining stability, response and functionality. However, they are challenging to computationally predict at Ab-Initio accuracy, even for elemental systems. Ab-Initio methods for modeling atomic…
In recent years, machine learning interatomic potentials (MLIPs) have attracted significant attention as a method that enables large-scale, long-time atomistic simulations while maintaining accuracy comparable to electronic structure…
The long-timescale behavior of complex dynamical systems can be described by linear Markov or Koopman models in a suitable latent space. Recent variational approaches allow the latent space representation and the linear dynamical model to…
Machine learning interatomic potentials (MLIPs) enable efficient molecular dynamics (MD) simulations with ab initio accuracy and have been applied across various domains in physical science. However, their performance often relies on…
Machine learning potentials (MLPs) are becoming powerful tools for performing accurate atomistic simulations and crystal structure optimizations. An approach to developing MLPs employs a systematic set of polynomial invariants including…
We discuss a method to solve models with long-range interactions in the microcanonical and canonical ensemble. The method closely follows the one introduced by Ellis, Physica D 133, 106 (1999), which uses large deviation techniques. We show…
Machine Learned Interatomic Potentials (MLIPs) offer a powerful combination of abilities for accelerating theoretical spectroscopy calculations utilising both ensemble sampling and trajectory post-processing for inclusion of vibronic…
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.…
Efficient materials discovery requires reducing costly first-principles calculations for training machine-learned interatomic potentials (MLIPs). We develop an active learning (AL) framework that iteratively selects informative structures…
Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods. However, without explicit supervision, which is often unavailable, the…
The universal mathematical form of machine-learning potentials (MLPs) shifts the core of development of interatomic potentials to collecting proper training data. Ideally, the training set should encompass diverse local atomic environments…
A novel data-driven methodology is presented for the joint selection of prior parameters for both fixed and random effects in Linear Mixed Models (LMMs). This approach facilitates the estimation of complex random-effects structures, as well…
The random batch Ewald (RBE) is an efficient and accurate method for molecular dynamics (MD) simulations of physical systems at the nano-/micro- scale. The method shows great potential to solve the computational bottleneck of long-range…
Free energy profiles serve as a fundamental bridge between microscopic atomic fluctuations and macroscopic thermodynamic observables. Estimating the free energy profile along a reaction coordinate, referred to as the potential of mean force…
Machine learning interatomic potentials (MLIPs) enable atomistic simulations with near ab initio accuracy at significantly reduced computational cost, but their broader adoption is often limited by fragmented tooling, limited scalability,…