paper-with-me

Papers

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

2024-05-31 · Jean Barbier, Francesco Camilli, Marco Mondelli, Yizhou Xu

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 proves to be challenging. To capture the structure while maintaining mathematical tractability, a line of work has focused on rotationally invariant noise. However, existing studies either provide sub-optimal algorithms or are limited to special cases of noise ensembles. In this paper, using tools from statistical physics (replica method) and random matrix theory (generalized spherical integrals) we establish the first 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.

📄 PDF Abstract BibTeX arXiv:2405.20993

Code (1)

xu-yz19/spiked-matrix-models-with-structured-noise 공식 구현

Tasks

Bayesian Inference

Similar Papers 제목 키워드 기반

Memory-free dynamics for the TAP equations of Ising models with arbitrary rotation invariant ensembles of random coupling matrices

2019-01-24 · Burak Çakmak, Manfred Opper

We propose an iterative algorithm for solving the Thouless-Anderson-Palmer (TAP) equations of Ising models with arbitrary rotation invariant (random) coupling matrices. In the thermodynamic limit, we prove by means of th…

Training Restricted Boltzmann Machine via the Thouless-Anderson-Palmer free energy

2015-12-01 · NeurIPS 2015 12 · Marylou Gabrie, Eric W. Tramel, Florent Krzakala

Restricted Boltzmann machines are undirected neural networks which have been shown tobe effective in many applications, including serving as initializations fortraining deep multi-layer neural networks. One of the main r…

Training Restricted Boltzmann Machines via the Thouless-Anderson-Palmer Free Energy

2015-06-09 · Marylou Gabrié, Eric W. Tramel, Florent Krzakala

Restricted Boltzmann machines are undirected neural networks which have been shown to be effective in many applications, including serving as initializations for training deep multi-layer neural networks. One of the main…

Bayes-optimal limits in structured PCA, and how to reach them

2022-10-03 · Jean Barbier, Francesco Camilli, Marco Mondelli, Manuel Saenz

How do statistical dependencies in measurement noise influence high-dimensional inference? To answer this, we study the paradigmatic spiked matrix model of principal components analysis (PCA), where a rank-one matrix is …

The TAP free energy for high-dimensional linear regression

2022-03-14 · Jiaze Qiu, Subhabrata Sen

We derive a variational representation for the log-normalizing constant of the posterior distribution in Bayesian linear regression with a uniform spherical prior and an i.i.d. Gaussian design. We work under the "proport…

regressionVocal Bursts Intensity Prediction