Selective Inference in Graphical Models via Maximum Likelihood

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guglielmini, Sofia, Claeskens, Gerda, Panigrahi, Snigdha
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916668003844096
author Guglielmini, Sofia
Claeskens, Gerda
Panigrahi, Snigdha
author_facet Guglielmini, Sofia
Claeskens, Gerda
Panigrahi, Snigdha
contents The graphical lasso is a widely used algorithm for fitting undirected Gaussian graphical models. However, for inference on functionals of edge values in the learned graph, standard tools lack formal statistical guarantees, such as control of the type I error rate. In this paper, we introduce a selective inference method for asymptotically valid inference after graphical lasso selection with added randomization. We obtain a selective likelihood, conditional on the event of selection, through a change of variable on the known density of the randomization variables. Our method enables interval estimation and hypothesis testing for a wide range of functionals of edge values in the learned graph using the conditional maximum likelihood estimate. Our numerical studies show that introducing a small amount of randomization: (i) greatly increases power and yields substantially shorter intervals compared to other conditional inference methods, including data splitting; (ii) ensures intervals of bounded length in high-dimensional settings where data splitting is infeasible due to insufficient samples for inference; (iii) enables inference for a wide range of inferential targets in the learned graph, including measures of node influence and connectivity between nodes.
format Preprint
id arxiv_https___arxiv_org_abs_2503_24311
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Selective Inference in Graphical Models via Maximum Likelihood
Guglielmini, Sofia
Claeskens, Gerda
Panigrahi, Snigdha
Methodology
Applications
Computation
The graphical lasso is a widely used algorithm for fitting undirected Gaussian graphical models. However, for inference on functionals of edge values in the learned graph, standard tools lack formal statistical guarantees, such as control of the type I error rate. In this paper, we introduce a selective inference method for asymptotically valid inference after graphical lasso selection with added randomization. We obtain a selective likelihood, conditional on the event of selection, through a change of variable on the known density of the randomization variables. Our method enables interval estimation and hypothesis testing for a wide range of functionals of edge values in the learned graph using the conditional maximum likelihood estimate. Our numerical studies show that introducing a small amount of randomization: (i) greatly increases power and yields substantially shorter intervals compared to other conditional inference methods, including data splitting; (ii) ensures intervals of bounded length in high-dimensional settings where data splitting is infeasible due to insufficient samples for inference; (iii) enables inference for a wide range of inferential targets in the learned graph, including measures of node influence and connectivity between nodes.
title Selective Inference in Graphical Models via Maximum Likelihood
topic Methodology
Applications
Computation
url https://arxiv.org/abs/2503.24311