Community detection and percolation of information in a geometric setting

We make the first steps towards generalizing the theory of stochastic block models, in the sparse regime, towards a model where the discrete community structure is replaced by an underlying geometry. We consider a geometric random graph over a homogeneous metric space where the probability of two vertices to be connected is an arbitrary function of the distance. We give sufficient conditions under which the locations can be recovered (up to an isomorphism of the space) in the sparse regime. Moreover, we define a geometric counterpart of the model of flow of information on trees, due to Mossel and Peres, in which one considers a branching random walk on a sphere and the goal is to recover the location of the root based on the locations of leaves. We give some sufficient conditions for percolation and for non-percolation of information in this model.

[1]  Claire Lacour,et al.  Minimax Adaptive Estimation of Nonparametric Geometric Graphs , 2017 .

[2]  R. Bhatia.  Matrix Analysis , 1996 .

[3]  Carey E. Priebe,et al.  Universally Consistent Latent Position Estimation and Vertex Classification for Random Dot Product Graphs , 2012, 1207.6745.

[4]  Joel A. Tropp,et al.  User-Friendly Tail Bounds for Sums of Random Matrices , 2010, Found. Comput. Math..

[5]  Tengyao Wang,et al.  A useful variant of the Davis--Kahan theorem for statisticians , 2014, 1405.0680.

[6]  Elchanan Mossel,et al.  Survey: Information Flow on Trees , 2004 .

[7]  Philip A. Ernst,et al.  On the Time for Brownian Motion to Visit Every Point on a Circle , 2013, 1312.4632.

[8]  Ernesto Araya Valdivia.  Relative concentration bounds for the spectrum of kernel matrices , 2018, 1812.02108.

[9]  C. Priebe,et al.  Universally consistent vertex classification for latent positions graphs , 2012, 1212.1182.

[10]  Ernesto Araya Valdivia.  Relative concentration bounds for the kernel matrix spectrum , 2018, ArXiv.

[11]  Yohann de Castro,et al.  Latent Distance Estimation for Random Geometric Graphs , 2019, NeurIPS.

[12]  Emmanuel Abbe,et al.  Community Detection and Stochastic Block Models , 2017, Found. Trends Commun. Inf. Theory.

[13]  Y. D. Castro,et al.  Adaptive estimation of nonparametric geometric graphs , 2017, Mathematical Statistics and Learning.

[14]  Mikio L. Braun,et al.  Accurate Error Bounds for the Eigenvalues of the Kernel Matrix , 2006, J. Mach. Learn. Res..

[15]  Elchanan Mossel,et al.  Information flow on trees , 2001, math/0107033.

[16]  Can M. Le,et al.  CONCENTRATION OF RANDOM GRAPHS AND APPLICATION TO COMMUNITY DETECTION , 2018, Proceedings of the International Congress of Mathematicians (ICM 2018).