Minimax Adaptive Estimation of Nonparametric Geometric Graphs

This article studies the recovery of graphons when they are convolution kernels on compact (symmetric) metric spaces. This case is of particular interest since it covers the situation where the probability of an edge depends only on some (unknown) function of the distance between latent points, referred to as Nonparametric Geometric Graphs (NGG). In this setting, almost minimax adaptive estimation of NGG is possible using a spectral procedure combined with a Goldenshluger-Lepski adaptation method.The latent spaces covered by our framework encompasses (among others) compact symmetric spaces of rank one, namely real spheres and projective spaces. For these latter, explicit computations of the eigenbasis and of the model complexity can be achieved, leading to quantitative non-asymptotic results. As a byproduct, the time complexity of our method scales cubicly in the size of the graph and exponentially in the regularity of the graphon. Hence, this paper offers an algorithmically and theoretically efficient procedure to estimate smooth NGG.