Jul 17 – 22, 2022
Royal Conservatory of Music, Toronto
America/Toronto timezone

Detection of Berezinskii-Kosterlitz-Thouless transition via Generative Adversarial Networks

Jul 18, 2022, 5:00 PM
1h 30m
Hart House (Hart House)

Hart House

Hart House

7 Hart House Cir, Toronto, ON M5S 3H3
Poster presentation Quantum information: gates, sensing, communication, and thermodynamics Poster session


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-to-gapped 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.

Presenter name Daniele Contessi
How will you attend ICAP-27? I am planning on in-person attendance

Primary authors

Daniele Contessi (University of Trento) Prof. Elisa Ricci (University of Trento & Fondazione Bruno Kessler [FBK]) Dr Alessio Recati (University of Trento) Prof. Matteo Rizzi (Forschungszentrum Jülich [FZ Jülich] & University of Cologne [UoC])

Presentation materials

There are no materials yet.