Metraipolis › archive › dc_baabc37ce326

Entangling power of neural networks — arXiv:2608.05293

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05293
License (as archived)
CC0-1.0
Archived
2026-10-31T10:53:53.496Z
SHA-256 of the archived text
93e72a6b409c1c937f5189a2aa60aca47360c39f33b937c896f1c81e5f2afbbe
Stable URL of this page
https://metraipolis.com/documento/dc_baabc37ce326

How to cite

Entangling power of neural networks — arXiv:2608.05293 — arXiv (en), https://arxiv.org/abs/2608.05293 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_baabc37ce326 (Metraipolis archive dc_baabc37ce326, sha256 93e72a6b409c1c937f5189a2aa60aca47360c39f33b937c896f1c81e5f2afbbe)
BibTeX
@misc{dcbaabc37ce326,
  title = {Entangling power of neural networks — arXiv:2608.05293},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05293},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_baabc37ce326; sha256 93e72a6b409c1c937f5189a2aa60aca47360c39f33b937c896f1c81e5f2afbbe},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05293. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Characterizing the complexity of correlations between subsystems is a fundamental task across information theory, machine learning, and science. In quantum physics, neural networks have found increasing application in learning wavefunctions. Here we introduce the entangling power of an encoder-decoder neural network, which quantifies its ability to generate entanglement between subsystems, dependent on a latent space dimension $K$ and the complexity class of the decoder. We exactly calculate this quantity for polynomial decoders of degree $p$ acting on a $K$-dimensional latent space. Our results establish the exponential entangling power of neural networks with modest resources. More broadly, our work provides a framework for analyzing correlations in machine learning that generalizes the notion of the Schmidt rank in entanglement theory.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-08-07 in quant-ph).
Categorie arXiv: Disordered Systems and Neural Networks (cond-mat.dis-nn) ; Quantum Physics (quant-ph).
Pagina del lavoro: https://arxiv.org/abs/2608.05293 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T10:40:45.635Z dalla pagina https://arxiv.org/catchup/quant-ph/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).