|
Activity Number:
|
184
- SPEED: Variable Selection and Networks
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 31, 2017 : 11:35 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistical Learning and Data Science
|
|
Abstract #325353
|
|
|
Title:
|
Structural Discovery in Temporal Networks
|
|
Author(s):
|
Shaojun Zhang* and George Michailidis
|
|
Companies:
|
University of Florida and University of Florida
|
|
Keywords:
|
temporal networks ;
low rank and sparse decomposition ;
fast algorithms
|
|
Abstract:
|
In many scientific domains, researchers acquire time series of network matrices that pose novel challenges to pattern extraction and visual exploration. We propose a novel decomposition that assumes a stable across time low-rank component and a sparse time-varying component. The latter can evolve in a smooth manner or exhibit sharp changes. We develop a fast alternating minimization algorithm and illustrate the results on synthetic and real data. The proposed decomposition enables to uncover the underlying network structure and display its temporal evolution.
|
Authors who are presenting talks have a * after their name.
