Threshold for Detecting High Dimensional Geometry in Anisotropic Random Geometric Graphs

  title={Threshold for Detecting High Dimensional Geometry in Anisotropic Random Geometric Graphs},
  author={Matthew Brennan and Guy Bresler and Brice Huang},
In the anisotropic random geometric graph model, vertices correspond to points drawn from a high-dimensional Gaussian distribution and two vertices are connected if their distance is smaller than a specified threshold. We study when it is possible to hypothesis test between such a graph and an Erd˝os-R´enyi graph with the same edge probability. If n is the number of vertices and α is the vector of eigenvalues, [EM19] shows that detection is possible when n 3 ≫ ( k α k 2 / k α k 3 ) 6 and… 



Phase transition in noisy high-dimensional random geometric graphs

The soft high-dimensional random geometric graph G(n, p, d, q), where each of the n vertices corresponds to an independent random point distributed uniformly on the sphere S, is considered, and the probability that two vertices are connected by an edge is a decreasing function of the Euclidean distance between the points.

Testing for high‐dimensional geometry in random graphs

The proof of the detection lower bound is based on a new bound on the total variation distance between a Wishart matrix and an appropriately normalized GOE matrix and a conjecture for the optimal detection boundary is made.

High-dimensional random geometric graphs and their clique number

It is shown that as the dimension grows, the graph becomes similar to an Erdos-Renyi random graph when the dimension is larger than $\log^3(n)$ where $n$ is the number of vertices.

Information and dimensionality of anisotropic random geometric graphs

A model of a random geometric graph in which vertices correspond to points generated randomly and independently from a non-isotropic d-dimensional Gaussian distribution, and two vertices are connected if the distance between them is smaller than some pre-specified threshold is studied.

Random geometric graphs.

An analytical expression for the cluster coefficient is derived, which shows that the graphs in which each vertex is assigned random coordinates in a geometric space of arbitrary dimensionality are distinctly different from standard random graphs, even for infinite dimensionality.

Entropic CLT and phase transition in high-dimensional Wishart matrices

An information theoretic phase transition is proved: high dimensional Wishart matrices are close in total variation distance to the corresponding Gaussian ensemble if and only if d is much larger than $n^3$ and the chain rule for relative entropy is used.

Phase transitions for detecting latent geometry in random graphs

It is proved that the random intersection graph converges in total variation to an Erdős–Rényi graph and is indistinguishable from simpler models without latent structure.

A CLT in Stein’s Distance for Generalized Wishart Matrices and Higher-Order Tensors

We study the convergence along the central limit theorem for sums of independent tensor powers, $\frac{1}{\sqrt{d}}\sum\limits_{i=1}^d X_i^{\otimes p}$. We focus on the high-dimensional regime where

The middle-scale asymptotics of Wishart matrices

We study the behavior of a real $p$-dimensional Wishart random matrix with $n$ degrees of freedom when $n,p\rightarrow\infty$ but $p/n\rightarrow 0$. We establish the existence of phase transitions

De Finetti-Style Results for Wishart Matrices: Combinatorial Structure and Phase Transitions

This paper identifies the precise threshold for d in terms of n for subsets of Wishart matrices to converge in total variation to independent Gaussians and determines the sharp threshold for a large family of $G$, including Erd\H{o}s-R\'enyi $G\sim G(n,p)$ at all values.