Title

Multivariate Inference of Network Moments by Subsamping.

Abstract

In this study, we delve into characterizing a population of networks through the lens of a single observed network, specifically using network motif counts or the corresponding network moments. Our focus is on the joint distribution of multiple network moments, which provides a multivariate perspective that captures the complex dependencies between motifs. This approach marks a significant shift from the marginal distributions examined in earlier research, enabling more accurate and robust inference about network characteristics. We present the use of node subsampling to approximate these joint distributions and prove that this approximation is asymptotically accurate. Through real-world applications, comparing gene networks and analyzing collaboration patterns within the statistical community, we illustrate that the joint distribution inference offers superior insights than marginal distributions, enhancing the understanding of network connection mechanisms.

Bio

I am currently a Ph.D student at the department of Statistics, University of Virginia.