Event
Comm, Control, Sig Process Seminar: Arya Mazumdar, "Learning Mixtures and Trace Reconstruction"
Thursday, September 17, 2020
1:00 p.m.-2:30 p.m.
Zoom online meeting
Ajaykrishnan Nageswaran
301 405 3661
ajayk@umd.edu
http://www.ece.umd.edu/seminars/ccsp/
Learning Mixtures and Trace Reconstruction
Speaker: Arya Mazumdar (University of Massachusetts, Amherst)
Time: 1:00 - 2:30 PM (EDT), Sep. 17
Zoom link: https://umd.zoom.us/j/92567614892
Abstract
We present a generic complex-analytic method of learning mixtures of distributions and apply it to learn Gaussian mixtures with shared variance, binomial mixtures with shared success probability, and Poisson mixtures, among others. The method was first introduced to reconstruct a sequence from their random subsequences, which is called the trace reconstruction problem. We show some new results in trace reconstruction and mention some further extensions of the complex analytic method in learning mixtures. If time permits, I will also describe some applications in recovering sparse signals from a mixture of responses.
The talk is primarily based on: https://arxiv.org/abs/1904.09618 and https://arxiv.org/abs/2001.06776.