The detection of phase transitions in quantum many-body systems with lowest possible prior knowledge of their details is among the most rousing goals of the flourishing application of machine-learning techniques to physical questions. Here, we train a Generative Adversarial Network (GAN) with the Entanglement Spectrum of a system bipartition, as extracted by means of Matrix Product States ansätze. We are able to identify gapless-togapped phase transitions in different one-dimensional models by looking at the machine inability to reconstruct outsider data with respect to the training set. We foresee that GAN-based methods will become instrumental in anomaly detection schemes applied to the determination of phase-diagrams.

Detection of Berezinskii-Kosterlitz-Thouless transition via generative adversarial networks / Contessi, D.; Ricci, E.; Recati, A.; Rizzi, M.. - In: SCIPOST PHYSICS. - ISSN 2542-4653. - 12:3(2022), pp. 10701-10717. [10.21468/SciPostPhys.12.3.107]

Detection of Berezinskii-Kosterlitz-Thouless transition via generative adversarial networks

Contessi D.;Ricci E.;Recati A.;
2022-01-01

Abstract

The detection of phase transitions in quantum many-body systems with lowest possible prior knowledge of their details is among the most rousing goals of the flourishing application of machine-learning techniques to physical questions. Here, we train a Generative Adversarial Network (GAN) with the Entanglement Spectrum of a system bipartition, as extracted by means of Matrix Product States ansätze. We are able to identify gapless-togapped phase transitions in different one-dimensional models by looking at the machine inability to reconstruct outsider data with respect to the training set. We foresee that GAN-based methods will become instrumental in anomaly detection schemes applied to the determination of phase-diagrams.
2022
3
Contessi, D.; Ricci, E.; Recati, A.; Rizzi, M.
Detection of Berezinskii-Kosterlitz-Thouless transition via generative adversarial networks / Contessi, D.; Ricci, E.; Recati, A.; Rizzi, M.. - In: SCIPOST PHYSICS. - ISSN 2542-4653. - 12:3(2022), pp. 10701-10717. [10.21468/SciPostPhys.12.3.107]
File in questo prodotto:
File Dimensione Formato  
SciPostPhys_12_3_107.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 2.59 MB
Formato Adobe PDF
2.59 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/341643
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 4
  • OpenAlex ND
social impact