English

Polynomial Threshold Functions of Bounded Tree-Width: Some Explainability and Complexity Aspects

Machine Learning 2025-01-15 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.2501.08297,
  title  = {Polynomial Threshold Functions of Bounded Tree-Width: Some Explainability and Complexity Aspects},
  author = {Karine Chubarian and Johnny Joyce and Gyorgy Turan},
  journal= {arXiv preprint arXiv:2501.08297},
  year   = {2025}
}

Comments

22 pages, 3 figures. To be published in Festschrift in honor of Johann A. Makowsky

R2 v1 2026-06-28T21:06:14.509Z