SEMINAR

Network Topology Inference

Speaker:

Eda BAYRAM

EPFL - Signal Processing Laboratory

Switzerland - 1015 Lausanne

Date Time Location: 06 January 2020, Monday. 14:00, Ayaslı Research Center

ARC210

ABSTRACT

Presentation will have two parts. The first part is an overview of the network

topology inference methods beginning with the inverse covariance estimation

with graphical Lasso. It continues with studies focusing on the statistical

inference of a graph structure underlying a set of observations captured on

the vertex space. The second part is based on Eda Bayram's recent work

<https://arxiv.org/abs/1910.10114> , which is about parametrizing a graph

learning problem by multi-relational information and learning a combination

of multi-layer graphs for the structure inference task.