NetKet: A machine learning toolkit for many-body quantum systems

Giuseppe Carleo (1) , Kenny Choo (2) , Damian Hofmann (3) , James E.T. Smith (4) , Tom Westerhout (5) , Fabien Alet (6, 7) , Emily Davis (8) , Stavros Efthymiou (9) , Ivan Glasser (9) , Sheng-Hsuan Lin (10) , Marta Mauri (1, 11) , Guglielmo Mazzola , Christian Mendl (12) , Evert van Nieuwenburg (13) , Ossian O’reilly (14) , Hugo Théveniaut (7, 6) , Giacomo Torlai (1) , Filippo Vicentini (15) , Alexander Wietek (1)

1 Flatiron Institute
2 UZH - Universität Zürich [Zürich] = University of Zurich
3 MPSD - Max Planck Institute for the Structure and Dynamics of Matter
4 University of Colorado [Boulder]
5 Radboud University [Nijmegen]
6 FFC - Fermions Fortement Corrélés (LPT)
7 LPT - Laboratoire de Physique Théorique
8 Stanford University
9 MPQ - Max-Planck-Institut für Quantenoptik
10 TUM - Technische Universität Munchen - Technical University Munich - Université Technique de Munich
11 UNIMI - Università degli Studi di Milano = University of Milan
12 TU Dresden - Technische Universität Dresden = Dresden University of Technology
13 CALTECH - California Institute of Technology
14 USC - University of Southern California
15 MPQ (UMR_7162) - Laboratoire Matériaux et Phénomènes Quantiques

We introduce NetKet, a comprehensive open source framework for the study of many-body quantum systems using machine learning techniques. The framework is built around a general and flexible implementation of neural-network quantum states, which are used as a variational ansatz for quantum wavefunctions. NetKet provides algorithms for several key tasks in quantum many-body physics and quantum technology, namely quantum state tomography, supervised learning from wavefunction data, and ground state searches for a wide range of customizable lattice models. Our aim is to provide a common platform for open research and to stimulate the collaborative development of computational methods at the interface of machine learning and many-body physics.

Mots clés: Neural-network quantum states; Variational Monte Carlo; Quantum state tomography; Machine learning; Supervised learning

Domaines: Physique [physics]; Matière Condensée [cond-mat]

Giuseppe Carleo, Kenny Choo, Damian Hofmann, James E.T. Smith, Tom Westerhout, et al.. NetKet: A machine learning toolkit for many-body quantum systems. SoftwareX, 2019, 10, pp.100311. ⟨10.1016/j.softx.2019.100311⟩. ⟨hal-02346742⟩