University of Michigan
EECS Department
Electrical and
Computer Engineering
EECS Building
1301 Beal Avenue
Ann Arbor, MI 481092122
CSP Seminar
Onebit matrix completion
Yaniv Plan
NSF Postdoc and Hildebrandt Assitant Professor
University of Michigan  Mathematics Department 

Thursday, October 24, 2013
4:00pm  5:00pm 1005 EECS


About the EventThe problem of recovering a matrix from an incomplete sampling of its entries—also known as matrix completion—arises in a wide variety of practical situations. In many of these settings, however, the observations are not only incomplete, but also highly quantized, often even to a single bit. Thus we ask, “Given just the signs of a subset of noisy entries of an unknown matrix, can the unknown matrix be reconstructed?” We show that under an approximate lowrank assumption, nuclearnorm constrained maximumlikelihood estimation gives a nearly minimax solution, and that in some regimes almost no information is lost by quantizing to a single bit.

BiographyYaniv Plan received his B.A. from the University of California, Berkeley in 2004 where he double majored in Applied Mathematics and Physics. He earned his Ph.D. in Applied and Computational Mathematics at Caltech in 2011 where he received the W.P. Carey and Co. Inc. prize for outstanding doctoral dissertation. He was also a Visiting Mathematical Researcher at Stanford in 20102011. He currently holds a Hildebrandt Assistant Professorship in Mathematics at the University of Michigan in conjunction with an NSF Postdoctoral Fellowship. His main areas of interest applied probability, theoretical statistics, compressive sensing, sparse approximation, lowrank matrix recovery, and nonasymptotic random matrix theory 
Additional Information
Contact: Ann Pace
Phone: 7635022
Email: ampace@umich.edu
Sponsor: University of Michigan, Department of Electrical Engineering & Computer Science
Open to: Public
Presentation: /systems/cspseminars/Plan_102413.pdf


