Metraipolis › archive › dc_fccacff14c7e

Information-Theoretic Limits for Rectangular Spiked Matrix Models with Rotationally Invariant Noise — arXiv:2610.16797

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.16797
License (as archived)
CC0-1.0
Archived
2026-10-16T10:29:08.318Z
SHA-256 of the archived text
545f92e1149bfe1651cc8209c5366073d1f29008155ca3b37f0b0f521ff70786
Stable URL of this page
https://metraipolis.com/documento/dc_fccacff14c7e

How to cite

Information-Theoretic Limits for Rectangular Spiked Matrix Models with Rotationally Invariant Noise — arXiv:2610.16797 — arXiv (en), https://arxiv.org/abs/2610.16797 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fccacff14c7e (Metraipolis archive dc_fccacff14c7e, sha256 545f92e1149bfe1651cc8209c5366073d1f29008155ca3b37f0b0f521ff70786)
BibTeX
@misc{dcfccacff14c7e,
  title = {Information-Theoretic Limits for Rectangular Spiked Matrix Models with Rotationally Invariant Noise — arXiv:2610.16797},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.16797},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fccacff14c7e; sha256 545f92e1149bfe1651cc8209c5366073d1f29008155ca3b37f0b0f521ff70786},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.16797. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the information-theoretic limits of inference in rectangular rank-one spiked matrix models with additive rotationally invariant noise, thereby going beyond the standard assumption of independent noise entries. Using the replica method from statistical physics, we derive a variational formula for the mutual information between the signal and the data, together with a system of saddle point equations predicting the minimum mean squared error in estimating the rank-one spike. We further show that, in the Bayes-optimal setting, these saddle point equations coincide with the fixed point equations of the state evolution of a recently proposed orthogonal approximate message passing algorithm with Bayes-optimal denoisers. This equivalence provides an algorithmic interpretation of the replica prediction and supports the Bayes-optimality of orthogonal approximate message passing whenever the relevant fixed point is unique. Numerical evaluations of the saddle point equations for several rotationally invariant noise ensembles and signal priors, together with finite-size simulations of the algorithm, confirm the asymptotic predictions. They illustrate both regimes with a unique informative fixed point, where orthogonal approximate message passing is predicted to attain the minimum mean squared error, and regimes with multiple fixed points, where a statistical-to-computational gap exists.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.ST, nuovi lavori del giorno).
Categorie arXiv: Information Theory (cs.IT) ; Disordered Systems and Neural Networks (cond-mat.dis-nn); Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2610.16797 — 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 2026-10-16T08:50:02.853Z dalla pagina https://arxiv.org/list/math.ST/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).