Alex Jung: Compressed Sensing for Learning from Big Data over Networks

This talk is part of the AScI Thematic programme "Challenges in Large Geometric Structures and Big Data".

Abstract:

In this talk, I present some of our most recent work on applying tools from compressed sensing to (semi-supervised) machine learning with massive network-structured datasets, i.e., big data over networks. We expect the use of compressed sensing ideas game changing as it was for digital signal processing. In particular, I will present a sparse label propagation algorithm which efficiently learns the labels for data points based on the availability of a few labeled training data points. This algorithm is inspired by compressed sensing recovery methods and allows for a simple sufficient condition on the network structure which guarantees accurate learning.

Alex Jung's talk "Compressed Sensing for Learning from Big Data over Networks" is part of the AScI Thematic programme "Challenges in Large Geometric Structures and Big Data".

Please see the Large Geometric Structures and Big Data @ AScI website for more information about this talk.