The Open Collections site will undergo maintenance from 4:00 PM - 6:00 PM PT on Wednesday, April 2nd, 2025. During this time, images and the IIIF service will not be available.

UBC Theses and Dissertations

UBC Theses Logo

UBC Theses and Dissertations

Graphical model structure learning using L₁-regularization Schmidt, Mark

Abstract

This work looks at fitting probabilistic graphical models to data when the structure is not known. The main tool to do this is L₁-regularization and the more general group L₁-regularization. We describe limited-memory quasi-Newton methods to solve optimization problems with these types of regularizers, and we examine learning directed acyclic graphical models with L₁-regularization, learning undirected graphical models with group L₁-regularization, and learning hierarchical log-linear models with overlapping group L₁-regularization.

Item Media

Item Citations and Data

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International