Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise

Documenti analoghi

• Information-theoretic limits and approximate message-passing for high-dimensional time series
  di: Tieplova, Daria, et al.
  Pubblicazione: (2025)
• A multiscale cavity method for sublinear-rank symmetric matrix factorization
  di: Barbier, Jean, et al.
  Pubblicazione: (2024)
• Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers
  di: Bassetti, Federico, et al.
  Pubblicazione: (2024)
• Joint parameter estimations for spin glasses
  di: Chen, Wei-Kuo, et al.
  Pubblicazione: (2024)
• Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime
  di: Camilli, Francesco, et al.
  Pubblicazione: (2025)