EcoSta 2022: Start Registration
View Submission - EcoSta2022
A0263
Title: Node aggregation in large-scale graphical models Authors:  Ines Wilms - Maastricht University (Netherlands) [presenting]
Jacob Bien - University of Southern California (United States)
Abstract: High-dimensional graphical models are often estimated using regularization by relying on edge sparsity as a simplifying assumption. We aggregate the nodes of the graphical model to produce parsimonious graphical models that provide an even simpler description of the dependence structure than would otherwise be possible. We develop a convex regularizer that estimates graphical models that are both edge-sparse and node-aggregated. The aggregation is performed in a data-driven fashion by leveraging side information in the form of a tree that encodes node similarity and facilitates the interpretation of the resulting aggregated nodes. We illustrate our proposal's practical advantages in simulations and applications.