200 citations · 384 across the 13 of their papers we have counts for
16 papers
Overcoming the limitations of body-ordered potentials for atomistic machine learning
Filippo Bigi, Michelangelo Domina, Maximilian Lloyd Ach +5
Machine-learning interatomic potentials have become indispensable tools in atomistic simulations. The most popular models rely heavily on physical priors, such as locality, smoothn…
Mechanistic study of mixed lithium halides solid state electrolytes
Davide Tisi, Sergey Pozdnyakov, Michele Ceriotti
Lithium halides with the general formula LiMX, where M indicates metal ions and X halide anions are very actively studied as solid-state electrolytes, because of relati…
Lookup multivariate Kolmogorov-Arnold Networks
Sergey Pozdnyakov, Philippe Schwaller
High-dimensional linear mappings, or linear layers, dominate both the parameter count and the computational cost of most modern deep-learning models. We introduce a general-purpose…
A universal machine learning model for the electronic density of states
Wei Bin How, Pol Febrer, Sanggyu Chong +5
In the last few years several ``universal'' interatomic potentials have appeared, using machine-learning approaches to predict energy and forces of atomic configurations with arbit…
PET-MAD, a lightweight universal interatomic potential for advanced materials modeling
Arslan Mazitov, Filippo Bigi, Matthias Kellner +6
Machine-learning interatomic potentials (MLIPs) have greatly extended the reach of atomic-scale simulations, offering the accuracy of first-principles calculations at a fraction of…
Probing the effects of broken symmetries in machine learning
Marcel F. Langer, Sergey N. Pozdnyakov, Michele Ceriotti
Symmetry is one of the most central concepts in physics, and it is no surprise that it has also been widely adopted as an inductive bias for machine-learning models applied to the…
Smooth, exact rotational symmetrization for deep learning on point clouds
Sergey N. Pozdnyakov, Michele Ceriotti
Point clouds are versatile representations of 3D objects and have found widespread application in science and engineering. Many successful deep-learning models have been proposed t…
Wigner kernels: body-ordered equivariant machine learning without a basis
Filippo Bigi, Sergey N. Pozdnyakov, Michele Ceriotti
Machine-learning models based on a point-cloud representation of a physical object are ubiquitous in scientific applications and particularly well-suited to the atomic-scale descri…
Completeness of Atomic Structure Representations
Jigyasa Nigam, Sergey N. Pozdnyakov, Kevin K. Huguenin-Dumittan +1
In this paper, we address the challenge of obtaining a comprehensive and symmetric representation of point particle groups, such as atoms in a molecule, which is crucial in physics…
Comment on "Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four body interactions"
Sergey N. Pozdnyakov, Michael J. Willatt, Albert P. Bartók +3
The "quasi-constant" SOAP and ACSF fingerprint manifolds recently discovered by Parsaeifard and Goedecker are a direct consequence of the presence of degenerate pairs of configurat…
Incompleteness of graph neural networks for points clouds in three dimensions
Sergey N. Pozdnyakov, Michele Ceriotti
Graph neural networks (GNN) are very popular methods in machine learning and have been applied very successfully to the prediction of the properties of molecules and materials. Fir…
Local invertibility and sensitivity of atomic structure-feature mappings
Sergey N. Pozdnyakov, Liwei Zhang, Christoph Ortner +2
The increasingly common applications of machine-learning schemes to atomic-scale simulations have triggered efforts to better understand the mathematical properties of the mapping…
Optimal radial basis for density-based atomic representations
Alexander Goscinski, Félix Musil, Sergey Pozdnyakov +1
The input of almost every machine learning algorithm targeting the properties of matter at the atomic scale involves a transformation of the list of Cartesian atomic coordinates in…
Recursive evaluation and iterative contraction of -body equivariant features
Jigyasa Nigam, Sergey Pozdnyakov, Michele Ceriotti
Mapping an atomistic configuration to an -point correlation of a field associated with the atomic positions (e.g. an atomic density) has emerged as an elegant and effective solu…
On the Completeness of Atomic Structure Representations
Sergey N. Pozdnyakov, Michael J. Willatt, Albert P. Bartók +3
Many-body descriptors are widely used to represent atomic environments in the construction of machine learned interatomic potentials and more broadly for fitting, classification an…
Fast general two- and three-body interatomic potential
Sergey Pozdnyakov, Artem R. Oganov, Efim Mazhnik +2
We introduce a new class of machine learning interatomic potentials - fast General Two- and Three-body Potential (GTTP), which is as fast as conventional empirical potentials and r…