Learning latent tree models with small query complexity
Statistics Theory
2025-08-12 v2 Statistics Theory
Abstract
We consider the problem of structure recovery in a graphical model of a tree where some variables are latent. Specifically, we focus on the Gaussian case, which can be reformulated as a well-studied problem: recovering a semi-labeled tree from a distance metric. We introduce randomized procedures that achieve query complexity of optimal order. Additionally, we provide statistical analysis for scenarios where the tree distances are noisy. The Gaussian setting can be extended to other situations, including the binary case and non-paranormal distributions.
Cite
@article{arxiv.2408.15624,
title = {Learning latent tree models with small query complexity},
author = {Luc Devroye and Gabor Lugosi and Piotr Zwiernik},
journal= {arXiv preprint arXiv:2408.15624},
year = {2025}
}