---
res:
  bibo_abstract:
  - 'We consider a prototypical problem of Bayesian inference for a structured spiked
    model: a low-rank signal is corrupted by additive noise. While both information-theoretic
    and algorithmic limits are well understood when the noise is a Gaussian Wigner
    matrix, the more realistic case of structured noise still remains challenging.
    To capture the structure while maintaining mathematical tractability, a line of
    work has focused on rotationally invariant noise. However, existing studies either
    provide suboptimal algorithms or are limited to a special class of noise ensembles.
    In this paper, using tools from statistical physics (replica method) and random
    matrix theory (generalized spherical integrals) we establish the characterization
    of the information-theoretic limits for a noise matrix drawn from a general trace
    ensemble. Remarkably, our analysis unveils the asymptotic equivalence between
    the rotationally invariant model and a surrogate Gaussian one. Finally, we show
    how to saturate the predicted statistical limits using an efficient algorithm
    inspired by the theory of adaptive Thouless-Anderson-Palmer (TAP) equations.@eng'
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Jean
      foaf_name: Barbier, Jean
      foaf_surname: Barbier
  - foaf_Person:
      foaf_givenName: Francesco
      foaf_name: Camilli, Francesco
      foaf_surname: Camilli
  - foaf_Person:
      foaf_givenName: Yizhou
      foaf_name: Xu, Yizhou
      foaf_surname: Xu
  - foaf_Person:
      foaf_givenName: Marco
      foaf_name: Mondelli, Marco
      foaf_surname: Mondelli
      foaf_workInfoHomepage: http://www.librecat.org/personId=27EB676C-8706-11E9-9510-7717E6697425
    orcid: 0000-0002-3242-7020
  bibo_doi: 10.1103/PhysRevResearch.7.013081
  bibo_volume: 7
  dct_date: 2025^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/2643-1564
  dct_language: eng
  dct_publisher: American Physical Society@
  dct_title: Information limits and Thouless-Anderson-Palmer equations for spiked
    matrix models with structured noise@
...