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

Vicentini, F.; Hofmann, D.; Szabó, A.; Wu, D.; Roth, C.; Giuliani, C.; Pescia, G.; Nys, J.; Vargas-Calderón, V.; Astrakhantsev, N.; Carleo, G.

doi:10.21468/SciPostPhysCodeb.7

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Journal Article

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

MPS-Authors

/persons/resource/persons241274

Hofmann, D.
Theoretical Description of Pump-Probe Spectroscopies in Solids, Theory Department, Max Planck Institute for the Structure and Dynamics of Matter, Max Planck Society;
Center for Free-Electron Laser Science (CFEL);

External Resource

https://arxiv.org/abs/2112.10526
(Preprint)

https://doi.org/10.21468/SciPostPhysCodeb.7
(Publisher version)

https://doi.org/10.21468/SciPostPhysCodeb.7-r3.4
(Code)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

SciPostPhysCodeb_7.pdf
(Publisher version), 843KB

Supplementary Material (public)

There is no public supplementary material available

Citation

Vicentini, F., Hofmann, D., Szabó, A., Wu, D., Roth, C., Giuliani, C., et al. (2022). NetKet 3: Machine Learning Toolbox for Many-Body Quantum Systems. SciPost Physics Codebases, 7. doi:10.21468/SciPostPhysCodeb.7.

Cite as: https://hdl.handle.net/21.11116/0000-000A-94B8-F

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.