Personne
Sergey Pozdnyakov
Publications associées (7)
Unified theory of atom-centered representations and message-passing machine-learning schemes
Michele Ceriotti, Guillaume André Jean Fraux, Sergey Pozdnyakov, Jigyasa Nigam
Data-driven schemes that associate molecular and crystal structures with their microscopic properties share the need for a concise, effective description of the arrangement of their atomic constituents. Many types of models rely on descriptions of atom-cen ...
AIP Publishing2022Comment on "Manifolds of quasi-constant SOAP and ACSF fingerprints and the resulting failure to machine learn four-body interactions" [J. Chem. Phys. 156, 034302 (2022)]
Michele Ceriotti, Sergey Pozdnyakov, Michael John Willatt
The "quasi-constant " smooth overlap of atomic position and atom-centered symmetry function fingerprint manifolds recently discovered by Parsaeifard and Goedecker [J. Chem. Phys. 156, 034302 (2022)] are closely related to the degenerate pairs of configurat ...
AIP Publishing2022Incompleteness of graph neural networks for points clouds in three dimensions
Michele Ceriotti, Sergey Pozdnyakov
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. First-order GNNs are well known to be incomplete, i.e. there exist graphs that ...
IOP Publishing Ltd2022Optimal radial basis for density-based atomic representations
Michele Ceriotti, Sergey Pozdnyakov, Jigyasa Nigam, Félix Benedito Clément Musil, Alexander Jan Goscinski
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 into a more symmetric representation. Many of the most popular representations ...
AIP Publishing2021Local invertibility and sensitivity of atomic structure-feature mappings
Michele Ceriotti, Sergey Pozdnyakov
Background: The increasingly common applications of machine-learning schemes to atomic-scale simulations have triggered efforts to better understand the mathematical properties of the mapping between the Cartesian coordinates of the atoms and the variety o ...
2021Incompleteness of Atomic Structure Representations
Michele Ceriotti, Sergey Pozdnyakov, Michael John Willatt
Many-body descriptors are widely used to represent atomic environments in the construction of machine-learned interatomic potentials and more broadly for fitting, classification, and embedding tasks on atomic structures. There is a widespread belief in the ...
AMER PHYSICAL SOC2020Recursive evaluation and iterative contraction of N-body equivariant features
Michele Ceriotti, Sergey Pozdnyakov, Jigyasa Nigam
Mapping an atomistic configuration to a symmetrized N-point correlation of a field associated with the atomic positions (e.g., an atomic density) has emerged as an elegant and effective solution to represent structures as the input of machine-learning algo ...
2020