Show simple item record

dc.contributor.authorReeves, Galen
dc.date.accessioned2019-09-09T18:53:48Z
dc.date.available2019-09-09T18:53:48Z
dc.date.issued2019-09-04
dc.identifier.urihttp://hdl.handle.net/1853/61835
dc.descriptionPresented on September 4, 2019 at 12:15 p.m. in the Marcus Nanotechnology Building, Room 1116.en_US
dc.descriptionGalen Reeves joined the faculty at Duke University in Fall 2013, and is currently an Assistant Professor with a joint appointment in the Department of Electrical & Computer Engineering and the Department of Statistical Science.en_US
dc.descriptionRuntime: 39:39 minutesen_US
dc.description.abstractThe information-theoretic limits of community detection have been studied extensively for network models with high levels of symmetry or homogeneity. In this talk, Reeves will present a new approach that applies to a broader class of network models that allow for variability in the sizes and behaviors of the different communities, and thus better reflect the behaviors observed in real-world networks. The results show that the ability to detect communities can be described succinctly in terms of a matrix of effective signal-to-noise ratios that provides a geometrical representation of the relationships between the different communities. This characterization follows from a matrix version of the I-MMSE relationship and generalizes the concept of an effective scalar signal-to-noise ratio introduced in previous work. This work can be found online at https://arxiv.org/abs/1907.02496en_US
dc.format.extent39:39 minutes
dc.language.isoen_USen_US
dc.relation.ispartofseriesMachine Learning @ Georgia Tech (ML@GT)en_US
dc.subjectCommunity detectionen_US
dc.subjectInformation theoryen_US
dc.subjectMachine learningen_US
dc.titleThe Geometry of Community Detection via the MMSE Matrixen_US
dc.typeLectureen_US
dc.typeVideoen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Machine Learningen_US
dc.contributor.corporatenameDuke University. Dept. of Electrical and Computer Engineeringen_US
dc.contributor.corporatenameDuke University. Dept. of Statistical Scienceen_US


Files in this item

Thumbnail
Thumbnail
Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record