22
216

Rate-optimal graphon estimation

Abstract

Network analysis is becoming one of the most active research areas in statistics. Significant advances have been made recently on developing theories, methodologies and algorithms for analyzing networks. However, there has been little fundamental study on optimal estimation. In this paper, we establish optimal rate of convergence for graphon estimation. For the stochastic block model with kk clusters, we show that the optimal rate under the mean squared error is n1logk+k2/n2n^{-1}\log k+k^2/n^2. The minimax upper bound improves the existing results in literature through a technique of solving a quadratic equation. When knlognk\leq\sqrt{n\log n}, as the number of the cluster kk grows, the minimax rate grows slowly with only a logarithmic order n1logkn^{-1}\log k. A key step to establish the lower bound is to construct a novel subset of the parameter space and then apply Fano's lemma, from which we see a clear distinction of the nonparametric graphon estimation problem from classical nonparametric regression, due to the lack of identifiability of the order of nodes in exchangeable random graph models. As an immediate application, we consider nonparametric graphon estimation in a H\"{o}lder class with smoothness α\alpha. When the smoothness α1\alpha\geq1, the optimal rate of convergence is n1lognn^{-1}\log n, independent of α\alpha, while for α(0,1)\alpha\in(0,1), the rate is n2α/(α+1)n^{-2\alpha/(\alpha+1)}, which is, to our surprise, identical to the classical nonparametric rate.

View on arXiv
Comments on this paper