2024/03/26 by Xifan Yu, Yu, Xifan, Ilias Zadik +3 · 1 citation
Computer Science · #Image and Object Detection Techniques #Machine Learning and Data Classification
paper · pdf · doi:10.48550/arxiv.2403.17766
We study the computational limits of the following general hypothesis testing problem. Let H=Hn be an arbitrary undirected graph on n vertices. We study the detection task between a ``null'' Erdős-Rényi random graph G(n,p) and a ``planted'' random graph which is the union of G(n,p) together with a random copy of H=Hn. Our notion of planted model is a generalization of a plethora of recently studied models initiated with the study of the planted clique model (Jerrum 1992), which corresponds to the special case where H is a k-clique and p=1/2. Over the last decade, several papers have studied the power of low-degree polynomials for limited choices of H's in the above task. In this work, we adopt a unifying perspective and characterize the power of constant degree polynomials for the detection task, when H=Hn is any arbitrary graph and for any p=Ω(1). Perhaps surprisingly, we prove that the optimal constant degree polynomial is always given by simply counting stars in the input random graph. As a direct corollary, we conclude that the class of constant-degree polynomials is only able to ``sense'' the degree distribution of the planted graph H, and no other graph theoretic property of it.