Work

Decision boundary for discrete Bayesian network classifiers

Year: 2015

Type: article

Abstract: Bayesian network classifiers are a powerful machine learning tool. In order to evaluate the expressive power of these models, we compute families of polynomials that sign-represent decision functions induced by Bayesian network classifiers. We prove that those families are linear combinations of products of Lagrange basis polynomials. In absence of V-structures in the predictor sub-graph, we are also able to prove that this family of polynomials does in- deed characterize the specific classifier considered. We then use this representation to bound the number of decision functions representable by Bayesian network classifiers with a given structure and we compare these bounds to the ones obtained using Vapnik-Chervonenkis dimension.

Source: LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)

DOI: 10.5555/2789272.2912086

Authors: Gherardo Varando, Concha Bielza, Pedro Larrañaga

Institution: Universidad Politécnica de Madrid

Language: English

Topic: Bayesian Modeling and Causal Inference

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Ministerio de Economía y Competitividad

Awards: G2228619995, G7015208893, G7288983138