Near-Optimal Degree Testing for Bayes Nets. (arXiv:2304.06733v1 [cs.LG])

This paper considers the problem of testing the maximum in-degree of the
Bayes net underlying an unknown probability distribution $P$ over $\{0,1\}^n$,
given sample access to $P$. We show that the sample complexity of the problem
is $\tilde{\Theta}(2^{n/2}/\varepsilon^2)$. Our algorithm relies on a
testing-by-learning framework, previously used to obtain sample-optimal
testers; in order to apply this framework, we develop new algorithms for
``near-proper'' learning of Bayes nets, and high-probability learning under
$\chi^2$ divergence, which are of independent interest.

algorithm algorithms apply arxiv bayes complexity distribution divergence framework independent near paper probability show testing