Learnability of Parameter-Bounded Bayes Nets

TL;DR

This paper investigates the computational complexity of learning parameter-bounded Bayes nets, proving NP-hardness for certain variants and providing sample complexity results for approximate recovery of such models.

Contribution

It extends NP-hardness results for learning Bayes nets and offers new sample complexity bounds for approximate learning of parameter-bounded Bayes nets.

Findings

NP-hardness of a promise variant of LEARN

Sample complexity bounds for approximate recovery

Generalization of previous degree-bounded sample complexity results

Abstract

Bayes nets are extensively used in practice to efficiently represent joint probability distributions over a set of random variables and capture dependency relations. In a seminal paper, Chickering et al. (JMLR 2004) showed that given a distribution $\mathbb{P}$, that is defined as the marginal distribution of a Bayes net, it is $\mathsf{NP}$-hard to decide whether there is a parameter-bounded Bayes net that represents $\mathbb{P}$. They called this problem LEARN. In this work, we extend the $\mathsf{NP}$-hardness result of LEARN and prove the $\mathsf{NP}$-hardness of a promise search variant of LEARN, whereby the Bayes net in question is guaranteed to exist and one is asked to find such a Bayes net. We complement our hardness result with a positive result about the sample complexity that is sufficient to recover a parameter-bounded Bayes net that is close (in TV distance) to a given distribution $\mathbb{P}$, that is represented by some parameter-bounded Bayes net, generalizing a degree-bounded sample complexity result of Brustle et al. (EC 2020).