English

Adaptive Estimation of Graphical Models under Total Positivity

Machine Learning 2023-06-12 v2 Machine Learning Signal Processing

Abstract

We consider the problem of estimating (diagonally dominant) M-matrices as precision matrices in Gaussian graphical models. These models exhibit intriguing properties, such as the existence of the maximum likelihood estimator with merely two observations for M-matrices \citep{lauritzen2019maximum,slawski2015estimation} and even one observation for diagonally dominant M-matrices \citep{truell2021maximum}. We propose an adaptive multiple-stage estimation method that refines the estimate by solving a weighted 1\ell_1-regularized problem at each stage. Furthermore, we develop a unified framework based on the gradient projection method to solve the regularized problem, incorporating distinct projections to handle the constraints of M-matrices and diagonally dominant M-matrices. A theoretical analysis of the estimation error is provided. Our method outperforms state-of-the-art methods in precision matrix estimation and graph edge identification, as evidenced by synthetic and financial time-series data sets.

Keywords

Cite

@article{arxiv.2210.15471,
  title  = {Adaptive Estimation of Graphical Models under Total Positivity},
  author = {Jiaxi Ying and José Vinícius de M. Cardoso and Daniel P. Palomar},
  journal= {arXiv preprint arXiv:2210.15471},
  year   = {2023}
}

Comments

26 pages

R2 v1 2026-06-28T04:38:55.467Z