|
Activity Number:
|
529
- Recent Advances in Clustering and Community Detection
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 6, 2020 : 1:00 PM to 2:50 PM
|
|
Sponsor:
|
WNAR
|
|
Abstract #309186
|
|
|
Title:
|
Community Estimation in Multilayer Stochastic Block Models
|
|
Author(s):
|
Jing Lei*
|
|
Companies:
|
Carnegie Mellon University
|
|
Keywords:
|
network;
multi-layer;
community detection;
consistency
|
|
Abstract:
|
In multi-layer network data, the relationships between pairs of elements are reflected in multiple modalities and may be described by multivariate or even high-dimensional vectors. Under the multi-layer stochastic block model, a fundamental question for statistical inference is how to optimally aggregate the information across different layers of data. Most existing methods require positivity for each individual layer to avoid signal cancellation in simple aggregation. In this work we consider least squares aggregation and study its asymptotic accuracy without assuming individual layer positivity. Some novel matrix concentration inequalities will also be developed.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2020 program
|
