Statistical Limits for the Matrix Tensor Product
Speaker: Professor Galen Reeves
Affiliation: Duke University
VIA ZOOM ONLY: https://ucla.zoom.us/j/96763629578?pwd=YVY2bVJRb1pNODVoa29jUDhkQTVHdz09
Departments of Statistical Science and Electrical and Computer Engineering, Duke University
Abstract:
High-dimensional models involving the products of large random matrices include the spiked matrix models appearing in principle component analysis and the stochastic block model appearing in network analysis. In this talk I will present some recent theoretical work that provides an asymptotically exact characterization of the fundamental limits of inference for a broad class of these models. The first part of the talk will introduce the “matrix tensor product” model and describe some implications of the theory for community detection in correlated networks. The second part will highlight some of the ideas in the analysis, which builds upon ideas from information theory and statistical physics.
The material in this talk is appears in following papers:
Information-Theoretic Limits for the Matrix Tensor Product, Galen Reeves
Mutual Information in Community Detection with Covariate Information and Correlated Networks, Vaishakhi Mayya and Galen Reeves
Date/Time:
Date(s) - Jan 14, 2021
11:00 am - 12:15 pm
Location:
Via Zoom Only
No location, Los Angeles
Map Unavailable