Foundation neural-networks quantum states as a unified Ansatz for multiple hamiltonians
Abstract Foundation models are highly versatile neural-network architectures capable of processing different data types, such as text and images, and generalizing across various tasks like classification and generation. Inspired by this success, we propose Foundation Neural-Network Quantum States (F...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-62098-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849235175496482816 |
|---|---|
| author | Riccardo Rende Luciano Loris Viteritti Federico Becca Antonello Scardicchio Alessandro Laio Giuseppe Carleo |
| author_facet | Riccardo Rende Luciano Loris Viteritti Federico Becca Antonello Scardicchio Alessandro Laio Giuseppe Carleo |
| author_sort | Riccardo Rende |
| collection | DOAJ |
| description | Abstract Foundation models are highly versatile neural-network architectures capable of processing different data types, such as text and images, and generalizing across various tasks like classification and generation. Inspired by this success, we propose Foundation Neural-Network Quantum States (FNQS) as an integrated paradigm for studying quantum many-body systems. FNQS leverage key principles of foundation models to define variational wave functions based on a single, versatile architecture that processes multimodal inputs, including spin configurations and Hamiltonian physical couplings. Unlike specialized architectures tailored for individual Hamiltonians, FNQS can generalize to physical Hamiltonians beyond those encountered during training, offering a unified framework adaptable to various quantum systems and tasks. FNQS enable the efficient estimation of quantities that are traditionally challenging or computationally intensive to calculate using conventional methods, particularly disorder-averaged observables. Furthermore, the fidelity susceptibility can be easily obtained to uncover quantum phase transitions without prior knowledge of order parameters. These pretrained models can be efficiently fine-tuned for specific quantum systems. The architectures trained in this paper are publicly available at https://huggingface.co/nqs-models , along with examples for implementing these neural networks in NetKet. |
| format | Article |
| id | doaj-art-cc3fd2579886492da08a60e573dd9722 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-cc3fd2579886492da08a60e573dd97222025-08-20T04:02:54ZengNature PortfolioNature Communications2041-17232025-08-0116111210.1038/s41467-025-62098-xFoundation neural-networks quantum states as a unified Ansatz for multiple hamiltoniansRiccardo Rende0Luciano Loris Viteritti1Federico Becca2Antonello Scardicchio3Alessandro Laio4Giuseppe Carleo5International School for Advanced Studies (SISSA)Institute of Physics, École Polytechnique Fédérale de Lausanne (EPFL)Dipartimento di Fisica, Università di TriesteThe Abdus Salam ICTPInternational School for Advanced Studies (SISSA)Institute of Physics, École Polytechnique Fédérale de Lausanne (EPFL)Abstract Foundation models are highly versatile neural-network architectures capable of processing different data types, such as text and images, and generalizing across various tasks like classification and generation. Inspired by this success, we propose Foundation Neural-Network Quantum States (FNQS) as an integrated paradigm for studying quantum many-body systems. FNQS leverage key principles of foundation models to define variational wave functions based on a single, versatile architecture that processes multimodal inputs, including spin configurations and Hamiltonian physical couplings. Unlike specialized architectures tailored for individual Hamiltonians, FNQS can generalize to physical Hamiltonians beyond those encountered during training, offering a unified framework adaptable to various quantum systems and tasks. FNQS enable the efficient estimation of quantities that are traditionally challenging or computationally intensive to calculate using conventional methods, particularly disorder-averaged observables. Furthermore, the fidelity susceptibility can be easily obtained to uncover quantum phase transitions without prior knowledge of order parameters. These pretrained models can be efficiently fine-tuned for specific quantum systems. The architectures trained in this paper are publicly available at https://huggingface.co/nqs-models , along with examples for implementing these neural networks in NetKet.https://doi.org/10.1038/s41467-025-62098-x |
| spellingShingle | Riccardo Rende Luciano Loris Viteritti Federico Becca Antonello Scardicchio Alessandro Laio Giuseppe Carleo Foundation neural-networks quantum states as a unified Ansatz for multiple hamiltonians Nature Communications |
| title | Foundation neural-networks quantum states as a unified Ansatz for multiple hamiltonians |
| title_full | Foundation neural-networks quantum states as a unified Ansatz for multiple hamiltonians |
| title_fullStr | Foundation neural-networks quantum states as a unified Ansatz for multiple hamiltonians |
| title_full_unstemmed | Foundation neural-networks quantum states as a unified Ansatz for multiple hamiltonians |
| title_short | Foundation neural-networks quantum states as a unified Ansatz for multiple hamiltonians |
| title_sort | foundation neural networks quantum states as a unified ansatz for multiple hamiltonians |
| url | https://doi.org/10.1038/s41467-025-62098-x |
| work_keys_str_mv | AT riccardorende foundationneuralnetworksquantumstatesasaunifiedansatzformultiplehamiltonians AT lucianolorisviteritti foundationneuralnetworksquantumstatesasaunifiedansatzformultiplehamiltonians AT federicobecca foundationneuralnetworksquantumstatesasaunifiedansatzformultiplehamiltonians AT antonelloscardicchio foundationneuralnetworksquantumstatesasaunifiedansatzformultiplehamiltonians AT alessandrolaio foundationneuralnetworksquantumstatesasaunifiedansatzformultiplehamiltonians AT giuseppecarleo foundationneuralnetworksquantumstatesasaunifiedansatzformultiplehamiltonians |