EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable representation learning of quantum data enabled by probabilistic variational autoencoders

Paulin de Schoulepnikoff, Gorka Muñoz-Gil, Hendrik Poulsen Nautrup, Hans J. Briegel

Physical Review A · 10.12.2025 · 112 (6)

DOI: 10.1103/cwb8-y25k ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physical Review A, online erschienen am 10.12.2025. Verfasst von Paulin de Schoulepnikoff und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Commission, European Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Interpretable machine learning is rapidly becoming a crucial tool for scientific discovery. Among existing approaches, variational autoencoders (VAEs) have shown promise in extracting the hidden physical features of some input data, with no supervision nor prior knowledge of the system at study. Yet the ability of VAEs to create meaningful, interpretable representations relies on their accurate approximation of the underlying probability distribution of their input. When dealing with quantum data, VAEs must hence account for its intrinsic randomness and complex correlations. While VAEs have been previously applied to quantum data, they have often neglected its probabilistic nature, hindering the extraction of meaningful physical descriptors. Here we demonstrate that two key modifications enable VAEs to learn physically meaningful latent representations: a decoder capable of faithfully reproducing the probability distributions of quantum states and a probabilistic loss tailored to this task. Using benchmark quantum spin models, we identify regimes where standard methods fail while the representations learned by our approach remain meaningful and interpretable. Applied to experimental data from Rydberg atom arrays, the model autonomously uncovers the phase structure without access to prior labels, Hamiltonian details, or knowledge of relevant order parameters, highlighting its potential as an unsupervised and interpretable tool for the study of quantum systems.

Förderung

  • European Commission
  • European Research Council

Zitieren

APA

Schoulepnikoff, P. D., Muñoz-Gil, G., Nautrup, H. P., & Briegel, H. J. (2025). Interpretable representation learning of quantum data enabled by probabilistic variational autoencoders. Physical Review A, 112(6). https://doi.org/10.1103/cwb8-y25k

Vancouver

Schoulepnikoff PD, Muñoz-Gil G, Nautrup HP, Briegel HJ. Interpretable representation learning of quantum data enabled by probabilistic variational autoencoders. Physical Review A. 2025;112(6). doi:10.1103/cwb8-y25k

BibTeX
@article{Schoulepnikoff2025,
  author = {Schoulepnikoff, Paulin de and Muñoz-Gil, Gorka and Nautrup, Hendrik Poulsen and Briegel, Hans J.},
  title = {Interpretable representation learning of quantum data enabled by probabilistic variational autoencoders},
  journal = {Physical Review A},
  year = {2025},
  volume = {112},
  number = {6},
  doi = {10.1103/cwb8-y25k}
}
Kostenlos starten →