Speaker: Jiajin Sun (Florida State University, Department of Statistics)

 

Title: (full article available by clicking:) Efficient Analysis of Latent Spaces in Heterogeneous Networks

 

 

Abstract: This work proposes a unified framework for efficient estimation under latent space modeling of heterogeneous networks. We consider a class of latent space models that decompose latent vectors into shared and network-specific components across networks. We develop a novel procedure that first identifies the shared latent vectors and further refines estimates through efficient score equations to achieve statistical efficiency. Oracle error rates for estimating the shared and heterogeneous latent vectors are established simultaneously. The analysis framework offers remarkable flexibility, accommodating various types of edge weights under general distributions.

 

 

Speaker Bio: Jiajin Sun is an Assistant Professor of Statistics at Florida State University. He earned his Ph.D. in Statistics at Columbia University in 2024. His research spans network analysis, high-dimensional statistics, and semiparametric statistics. 

 

 

 

SDS seminar’s website: https://auburn.edu/cosam/datascienceseminar/index.htm