Compressive Recovery of Sparse Precision Matrices - Inria - Institut national de recherche en sciences et technologies du numérique
Preprints, Working Papers, ... Year : 2023

Compressive Recovery of Sparse Precision Matrices

Abstract

We consider the problem of learning a graph modeling the statistical relations of the $d$ variables of a dataset with $n$ samples $\mathbf{X} \in \mathbb{R}^{n \times d}$. Standard approaches amount to searching for a precision matrix $\Theta$ representative of a Gaussian graphical model that adequately explains the data. However, most maximum likelihood-based estimators usually require storing the $d^{2}$ values of the empirical covariance matrix, which can become prohibitive in a high-dimensional setting. In this work, we adopt a ‘‘compressive'' viewpoint and aim to estimate a sparse $\Theta$ from a sketch of the data, \textit{i.e.} a low-dimensional vector of size $m \ll d^{2}$ carefully designed from $\mathbf{X}$ using nonlinear random features. Under certain assumptions on the spectrum of $\Theta$ (or its condition number), we show that it is possible to estimate it from a sketch of size $m=\Omega\left((d+2k)\log(d)\right)$ where $k$ is the maximal number of edges of the underlying graph. These information-theoretic guarantees are inspired by compressed sensing theory and involve restricted isometry properties and instance optimal decoders. We investigate the possibility of achieving practical recovery with an iterative algorithm based on the graphical lasso, viewed as a specific denoiser. We compare our approach and graphical lasso on synthetic datasets, demonstrating its favorable performance even when the dataset is compressed.
Fichier principal
Vignette du fichier
ima_preprint.pdf (834.78 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04275341 , version 1 (08-11-2023)
hal-04275341 , version 2 (11-12-2023)
hal-04275341 , version 3 (12-12-2023)

Identifiers

Cite

Titouan Vayer, Etienne Lasalle, Rémi Gribonval, Paulo Gonçalves. Compressive Recovery of Sparse Precision Matrices. 2023. ⟨hal-04275341v3⟩
119 View
77 Download

Altmetric

Share

More