BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251018T081819EDT-8631j30e6v@132.216.98.100
DTSTAMP:20251018T121819Z
DESCRIPTION:Large-scale Network Inference\n\n\n	Abstract:\n\n\nNetwork data 
 is prevalent in many contemporary big data applications in which a common 
 interest is to unveil important latent links between different pairs of no
 des. Yet a simple fundamental question of how to precisely quantify the st
 atistical uncertainty associated with the identification of latent links s
 till remains largely unexplored. In this paper\, we propose the method of 
 statistical inference on membership profiles in large networks (SIMPLE) in
  the setting of degree-corrected mixed membership model\, where the null h
 ypothesis assumes that the pair of nodes share the same profile of communi
 ty memberships. In the simpler case of no degree heterogeneity\, the model
  reduces to the mixed membership model for which an alternative more robus
 t test is also proposed. Both tests are of the Hotelling-type statistics b
 ased on the rows of empirical eigenvectors or their ratios\, whose asympto
 tic covariance matrices are very challenging to derive and estimate. Never
 theless\, their analytical expressions are unveiled and the unknown covari
 ance matrices are consistently estimated. Under some mild regularity condi
 tions\, we establish the exact limiting distributions of the two forms of 
 SIMPLE test statistics under the null hypothesis and contiguous alternativ
 e hypothesis. They are the chi-square distributions and the noncentral chi
 -square distributions\, respectively\, with degrees of freedom depending o
 n whether the degrees are corrected or not. We also address the important 
 issue of estimating the unknown number of communities and establish the as
 ymptotic properties of the associated test statistics. The advantages and 
 practical utility of our new procedures in terms of both size and power ar
 e demonstrated through several simulation examples and real network applic
 ations.\n\nThis talk is based on joint works with Jianqing Fan\, Xiao Han 
 and Jinchi Lv.\n\n\n	Speaker\n\n\nYingying Fan is Professor and Dean’s Asso
 ciate Professor in Business Administration in Data Sciences and Operations
  Department at USC Marshall\, Professor of Economics and Computer Science 
 at USC\, and an Associate Fellow of USC INET. She received her Ph.D. in Op
 erations Research and Financial Engineering from Princeton University in 2
 007. She was Lecturer in the Department of Statistics at Harvard Universit
 y (2007-2008). Her research interests include statistics\, data science\, 
 machine learning\, economics\, big data and business applications\, and ar
 tificial intelligence. Her papers have been published in journals in stati
 stics\, economics\, computer science\, and information theory.\n\nZoom Lin
 k\n\nMeeting ID: 939 4707 7997\n\nPasscode: no password\n\n \n\n \n
DTSTART:20200925T180000Z
DTEND:20200925T190000Z
SUMMARY:Yingying Fan (USC) Marshall
URL:/mathstat/channels/event/yingying-fan-usc-marshall
 -324831
END:VEVENT
END:VCALENDAR