Date & Time:
Friday, December 2, 2016; 11:00 AM
While distributed information processing has a rich history, relatively less attention has been paid to the problem of collaborative learning of nonlinear geometric structures underlying data distributed across sites that are connected to each other in an arbitrary topology. In this talk, we discuss this problem in the context of collaborative dictionary learning from big, distributed data. It is assumed that a number of geographically-distributed, interconnected sites have massive local data and they are interested in collaboratively learning a low-dimensional geometric structure underlying these data. In contrast to some of the previous works on subspace-based data representations, we focus on the geometric structure of a union of subspaces (UoS). In this regard, we propose a distributed algorithm, termed cloud K-SVD, for collaborative learning of a UoS structure underlying distributed data of interest. The goal of cloud K-SVD is to learn an overcomplete dictionary at each individual site such that every sample in the distributed data can be represented through a small number of atoms of the learned dictionary. Cloud K-SVD accomplishes this goal without requiring communication of individual data samples between different sites. In this talk, we also theoretically characterize deviations of the dictionaries learned at individual sites by cloud K-SVD from a centralized solution. Finally, we numerically illustrate the efficacy of cloud K-SVD in the context of supervised training of nonlinear classsifiers from distributed, labaled training data.
Prof. Waheed Bajwa
Waheed U. Bajwa received BE (with Honors) degree in electrical engineering from the National University of Sciences and Technology, Pakistan in 2001, and MS and PhD degrees in electrical engineering from the University of Wisconsin-Madison in 2005 and 2009, respectively. He was a Postdoctoral Research Associate in the Program in Applied and Computational Mathematics at Princeton University from 2009 to 2010, and a Research Scientist in the Department of Electrical and Computer Engineering at Duke University from 2010 to 2011. He is currently an Assistant Professor in the Department of Electrical and Computer Engineering at Rutgers University. His research interests include harmonic analysis, high-dimensional statistics, machine learning, statistical signal processing, and wireless communications.
Dr. Bajwa has more than three years of industry experience, including a summer position at GE Global Research, Niskayuna, NY. He received the Best in Academics Gold Medal and President's Gold Medal in Electrical Engineering from the National University of Sciences and Technology in 2001, the Morgridge Distinguished Graduate Fellowship from the University of Wisconsin-Madison in 2003, the Army Research Office Young Investigator Award in 2014, the National Science Foundation CAREER Award in 2015, and the Rutgers University?s Presidential Merit Award and Rutgers Engineering Governing Council ECE Professor of the Year Award in 2016. He is a co-author on the paper that received the Best Student Paper Award at the IEEE IVMSP 2016 Workshop, and he was selected as a Member of the Class of 2015 National Academy of Engineering Frontiers of Engineering Education Symposium. He co-guest edited a special issue of Elsevier Physical Communication Journal on ?Compressive Sensing in Communications? (2012), co-chaired CPSWeek 2013 Workshop on Signal Processing Advances in Sensor Networks and IEEE GlobalSIP 2013 Symposium on New Sensing and Statistical Inference Methods, and served as the Publicity and Publications Chair of IEEE CAMSAP 2015. He is an Associate Editor of the IEEE Signal Processing Letters, a Senior Member of the IEEE, and serves on the MLSP, SAM, and SPCOM Technical Committees of the IEEE Signal Processing Society.