Header

UZH-Logo

Maintenance Infos

NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems


Vicentini, Filippo; Hofmann, Damian; Szabó, Attila J; Wu, Dian; Roth, Christopher P; Giuliani, Clemens; Pescia, Gabriel; Nys, Jannes; Vargas-Calderón, Vladimir; Astrakhantsev, Nikita; Carleo, Giuseppe (2022). NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems. SciPost Physics Codebases:7.

Abstract

We introduce version 3 of NetKet, the machine learning toolbox for many-body quantum physics. NetKet is built around neural-network quantum states and provides efficient algorithms for their evaluation and optimization. This new version is built on top of JAX, a differentiable programming and accelerated linear algebra framework for the Python programming language. The most significant new feature is the possibility to define arbitrary neural network ansätze in pure Python code using the concise notation of machine-learning frameworks, which allows for just-in-time compilation as well as the implicit generation of gradients thanks to automatic differentiation. NetKet 3 also comes with support for GPU and TPU accelerators, advanced support for discrete symmetry groups, chunking to scale up to thousands of degrees of freedom, drivers for quantum dynamics applications, and improved modularity, allowing users to use only parts of the toolbox as a foundation for their own code.

Abstract

We introduce version 3 of NetKet, the machine learning toolbox for many-body quantum physics. NetKet is built around neural-network quantum states and provides efficient algorithms for their evaluation and optimization. This new version is built on top of JAX, a differentiable programming and accelerated linear algebra framework for the Python programming language. The most significant new feature is the possibility to define arbitrary neural network ansätze in pure Python code using the concise notation of machine-learning frameworks, which allows for just-in-time compilation as well as the implicit generation of gradients thanks to automatic differentiation. NetKet 3 also comes with support for GPU and TPU accelerators, advanced support for discrete symmetry groups, chunking to scale up to thousands of degrees of freedom, drivers for quantum dynamics applications, and improved modularity, allowing users to use only parts of the toolbox as a foundation for their own code.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

66 downloads since deposited on 05 Sep 2022
9 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, not_refereed, original work
Communities & Collections:07 Faculty of Science > Physics Institute
Dewey Decimal Classification:530 Physics
Uncontrolled Keywords:Biochemistry, Analytical Chemistry, General Energy, Nutrition and Dietetics, Medicine (miscellaneous), Colloid and Surface Chemistry, Polymers and Plastics, Physical and Theoretical Chemistry, Surfaces and Interfaces, Critical Care and Intensive Care Medicine, Electrochemistry, Analytical Chemistry, Endocrinology, Diabetes and Metabolism, Endocrinology, Endocrinology, Diabetes and Metabolism, Internal Medicine, General Medicine, Anesthesiology and Pain Medicine, Critical Care and Intensive Care Medicine
Language:English
Date:24 August 2022
Deposited On:05 Sep 2022 15:08
Last Modified:18 Dec 2023 13:59
Publisher:SciPost
ISSN:2949-804X
OA Status:Hybrid
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.21468/SciPostPhysCodeb.7
Project Information:
  • : FunderMicrosoft Research
  • : Grant ID
  • : Project Title
  • : FunderSNSF
  • : Grant ID200021_200336
  • : Project TitleMachine Learning Simulation of Many-Body Quantum Matter
  • Content: Published Version
  • Language: English
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)