no code implementations • 4 Mar 2024 • Filippo Bigi, Sanggyu Chong, Michele Ceriotti, Federico Grasselli
Regression methods are fundamental for scientific and technological applications.
no code implementations • 1 Nov 2023 • Edoardo Cignoni, Divya Suman, Jigyasa Nigam, Lorenzo Cupellini, Benedetta Mennucci, Michele Ceriotti
Data-driven techniques are increasingly used to replace electronic-structure calculations of matter.
no code implementations • 25 Aug 2023 • Kevin K. Huguenin-Dumittan, Philip Loche, Ni Haoran, Michele Ceriotti
One essential ingredient in many machine learning (ML) based methods for atomistic modeling of materials and molecules is the use of locality.
no code implementations • NeurIPS 2023 • Sergey N. Pozdnyakov, Michele Ceriotti
Point clouds are versatile representations of 3D objects and have found widespread application in science and engineering.
no code implementations • 7 Mar 2023 • 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 description of molecules and materials.
Ranked #2 on Formation Energy on QM9
no code implementations • 28 Feb 2023 • Jigyasa Nigam, Sergey N. Pozdnyakov, Kevin K. Huguenin-Dumittan, Michele Ceriotti
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 and theoretical chemistry.
1 code implementation • 16 Feb 2023 • Filippo Bigi, Guillaume Fraux, Nicholas J. Browning, Michele Ceriotti
Spherical harmonics provide a smooth, orthogonal, and symmetry-adapted basis to expand functions on a sphere, and they are used routinely in physical and theoretical chemistry as well as in different fields of science and technology, from geology and atmospheric sciences to signal processing and computer graphics.
no code implementations • 21 Sep 2022 • Rose K. Cersonsky, Maria Pakhnova, Edgar A. Engel, Michele Ceriotti
Due to the subtle balance of intermolecular interactions that govern structure-property relations, predicting the stability of crystal structures formed from molecular building blocks is a highly non-trivial scientific problem.
no code implementations • 5 Sep 2022 • Filippo Bigi, Kevin Huguenin-Dumittan, Michele Ceriotti, David E. Manolopoulos
Machine learning frameworks based on correlations of interatomic positions begin with a discretized description of the density of other atoms in the neighbourhood of each atom in the system.
1 code implementation • 28 Jun 2022 • Andrea Grisafi, Alan M. Lewis, Mariana Rossi, Michele Ceriotti
The electron density of a molecule or material has recently received major attention as a target quantity of machine-learning models.
no code implementations • 11 May 2022 • Chiheb Ben Mahmoud, Federico Grasselli, Michele Ceriotti
Machine-learning potentials are usually trained on the ground-state, Born-Oppenheimer energy surface, which depends exclusively on the atomic positions and not on the simulation temperature.
no code implementations • 3 Feb 2022 • Jigyasa Nigam, Sergey Pozdnyakov, Guillaume Fraux, Michele Ceriotti
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.
no code implementations • 18 Jan 2022 • Sergey N. Pozdnyakov, Michele Ceriotti
We construct pairs of distinct point clouds whose associated graphs are, for any cutoff radius, equivalent based on a first-order Weisfeiler-Lehman test.
no code implementations • 24 Sep 2021 • Jigyasa Nigam, Michael Willatt, Michele Ceriotti
Symmetry considerations are at the core of the major frameworks used to provide an effective mathematical representation of atomic configurations that is then used in machine-learning models to predict the properties associated with each structure.
no code implementations • 18 May 2021 • Alexander Goscinski, Félix Musil, Sergey Pozdnyakov, Michele Ceriotti
For each training dataset and number of basis functions, one can determine a unique basis that is optimal in this sense, and can be computed at no additional cost with respect to the primitive basis by approximating it with splines.
no code implementations • 12 Jan 2021 • Felix Musil, Andrea Grisafi, Albert P. Bartók, Christoph Ortner, Gábor Csányi, Michele Ceriotti
The first step in the construction of a regression model or a data-driven analysis, aiming to predict or elucidate the relationship between the atomic scale structure of matter and its properties, involves transforming the Cartesian coordinates of the atoms into a suitable representation.
Chemical Physics
1 code implementation • 22 Dec 2020 • Rose K. Cersonsky, Benjamin A. Helfrecht, Edgar A. Engel, Michele Ceriotti
Selecting the most relevant features and samples out of a large set of candidates is a task that occurs very often in the context of automated data analysis, where it can be used to improve the computational performance, and also often the transferability, of a model.
no code implementations • 8 Dec 2020 • Félix Musil, Michele Ceriotti
Statistical learning algorithms are finding more and more applications in science and technology.
Chemical Physics Computational Physics
1 code implementation • 10 Nov 2020 • Giulio Imbalzano, Yongbin Zhuang, Venkat Kapil, Kevin Rossi, Edgar A. Engel, Federico Grasselli, Michele Ceriotti
Given the interpolative nature of these models, the reliability of predictions depends on the position in phase space, and it is crucial to obtain an estimate of the error that derives from the finite number of reference structures included during the training of the model.
2 code implementations • 6 Sep 2020 • Alexander Goscinski, Guillaume Fraux, Giulio Imbalzano, Michele Ceriotti
In this work we introduce a framework to compare different sets of descriptors, and different ways of transforming them by means of metrics and kernels, in terms of the structure of the feature space that they induce.
no code implementations • 27 Aug 2020 • Andrea Grisafi, Jigyasa Nigam, Michele Ceriotti
Electronic nearsightedness is one of the fundamental principles governing the behavior of condensed matter and supporting its description in terms of local entities such as chemical bonds.
no code implementations • 7 Jul 2020 • Jigyasa Nigam, Sergey Pozdnyakov, Michele Ceriotti
While it has become clear that low-order density correlations do not provide a complete representation of an atomic environment, the exponential increase in the number of possible $N$-body invariants makes it difficult to design a concise and effective representation.
Chemical Physics
no code implementations • 21 Jun 2020 • Chiheb Ben Mahmoud, Andrea Anelli, Gábor Csányi, Michele Ceriotti
The electronic density of states (DOS) quantifies the distribution of the energy levels that can be occupied by electrons in a quasiparticle picture, and is central to modern electronic structure theory.
1 code implementation • 27 Mar 2020 • Max Veit, David M. Wilkins, Yang Yang, Robert A. DiStasio Jr., Michele Ceriotti
In this work, we choose to represent this quantity with a physically inspired ML model that captures two distinct physical effects: local atomic polarization is captured within the symmetry-adapted Gaussian process regression (SA-GPR) framework, which assigns a (vector) dipole moment to each atom, while movement of charge across the entire molecule is captured by assigning a partial (scalar) charge to each atom.
no code implementations • 12 Feb 2020 • Benjamin A. Helfrecht, Rose K. Cersonsky, Guillaume Fraux, Michele Ceriotti
Data analyses based on linear methods constitute the simplest, most robust, and transparent approaches to the automatic processing of large amounts of data for building supervised or unsupervised machine learning models.
2 code implementations • 21 Nov 2018 • Bingqing Cheng, Edgar A. Engel, Jörg Behler, Christoph Dellago, Michele Ceriotti
Thermodynamic properties of liquid water as well as hexagonal (Ih) and cubic (Ic) ice are predicted based on density functional theory at the hybrid-functional level, rigorously taking into account quantum nuclear motion, anharmonic fluctuations and proton disorder.
Materials Science Statistical Mechanics Chemical Physics
1 code implementation • 28 Dec 2015 • Sandip De, Albert P. Bartók, Gábor Csányi, Michele Ceriotti
For instance, a structural similarity metric is crucial for classifying structures, searching chemical space for better compounds and materials, and driving the next generation of machine-learning techniques for predicting the stability and properties of molecules and materials.
Materials Science Chemical Physics