Saved in:
Bibliographic Details
Main Authors: Chubarian, Karine, Joyce, Johnny, Turan, Gyorgy
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.08297
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913649688313856
author Chubarian, Karine
Joyce, Johnny
Turan, Gyorgy
author_facet Chubarian, Karine
Joyce, Johnny
Turan, Gyorgy
contents The tree-width of a multivariate polynomial is the tree-width of the hypergraph with hyperedges corresponding to its terms. Multivariate polynomials of bounded tree-width have been studied by Makowsky and Meer as a new sparsity condition that allows for polynomial solvability of problems which are intractable in general. We consider a variation on this theme for Boolean variables. A representation of a Boolean function as the sign of a polynomial is called a polynomial threshold representation. We discuss Boolean functions representable as polynomial threshold functions of bounded tree-width and present two applications to Bayesian network classifiers, a probabilistic graphical model. Both applications are in Explainable Artificial Intelligence (XAI), the research area dealing with the black-box nature of many recent machine learning models. We also give a separation result between the representational power of positive and general polynomial threshold functions.
format Preprint
id arxiv_https___arxiv_org_abs_2501_08297
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Polynomial Threshold Functions of Bounded Tree-Width: Some Explainability and Complexity Aspects
Chubarian, Karine
Joyce, Johnny
Turan, Gyorgy
Machine Learning
Artificial Intelligence
The tree-width of a multivariate polynomial is the tree-width of the hypergraph with hyperedges corresponding to its terms. Multivariate polynomials of bounded tree-width have been studied by Makowsky and Meer as a new sparsity condition that allows for polynomial solvability of problems which are intractable in general. We consider a variation on this theme for Boolean variables. A representation of a Boolean function as the sign of a polynomial is called a polynomial threshold representation. We discuss Boolean functions representable as polynomial threshold functions of bounded tree-width and present two applications to Bayesian network classifiers, a probabilistic graphical model. Both applications are in Explainable Artificial Intelligence (XAI), the research area dealing with the black-box nature of many recent machine learning models. We also give a separation result between the representational power of positive and general polynomial threshold functions.
title Polynomial Threshold Functions of Bounded Tree-Width: Some Explainability and Complexity Aspects
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2501.08297