Graphical Modelling without Independence Assumptions for Uncentered Data

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Andrew, Bailey, Westhead, David R., Cutillo, Luisa
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911977349054464
author Andrew, Bailey
Westhead, David R.
Cutillo, Luisa
author_facet Andrew, Bailey
Westhead, David R.
Cutillo, Luisa
contents The independence assumption is a useful tool to increase the tractability of one's modelling framework. However, this assumption does not match reality; failing to take dependencies into account can cause models to fail dramatically. The field of multi-axis graphical modelling (also called multi-way modelling, Kronecker-separable modelling) has seen growth over the past decade, but these models require that the data have zero mean. In the multi-axis case, inference is typically done in the single sample scenario, making mean inference impossible. In this paper, we demonstrate how the zero-mean assumption can cause egregious modelling errors, as well as propose a relaxation to the zero-mean assumption that allows the avoidance of such errors. Specifically, we propose the "Kronecker-sum-structured mean" assumption, which leads to models with nonconvex-but-unimodal log-likelihoods that can be solved efficiently with coordinate descent.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02393
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Graphical Modelling without Independence Assumptions for Uncentered Data
Andrew, Bailey
Westhead, David R.
Cutillo, Luisa
Methodology
Machine Learning
The independence assumption is a useful tool to increase the tractability of one's modelling framework. However, this assumption does not match reality; failing to take dependencies into account can cause models to fail dramatically. The field of multi-axis graphical modelling (also called multi-way modelling, Kronecker-separable modelling) has seen growth over the past decade, but these models require that the data have zero mean. In the multi-axis case, inference is typically done in the single sample scenario, making mean inference impossible. In this paper, we demonstrate how the zero-mean assumption can cause egregious modelling errors, as well as propose a relaxation to the zero-mean assumption that allows the avoidance of such errors. Specifically, we propose the "Kronecker-sum-structured mean" assumption, which leads to models with nonconvex-but-unimodal log-likelihoods that can be solved efficiently with coordinate descent.
title Graphical Modelling without Independence Assumptions for Uncentered Data
topic Methodology
Machine Learning
url https://arxiv.org/abs/2408.02393