Deep Generative Models and Inverse Problems
ECE 595 Department Distinguished Lecturer Seminar Series
December 4, 2020
11:00 AM - 12:00 PM
Location
online: https://us.bbcollab.com/collab/ui/session/guest/11c4db8fd1e64805a7a7c337715fb861
Address
Chicago, IL 60607
Calendar
Download iCal FileDeep Generative Models and Inverse Problems
Presenter: Alexandros G. Dimakis, University of Texas, Austin
Abstract: Modern deep generative models like GANs, VAEs and invertible flows are achieving amazing results on modeling high-dimensional distributions, especially for images. In this lecture, you will learn how they can be used to solve inverse problems by generalizing compressed sensing beyond sparsity, extending the theory of Restricted Isometries to sets created by generative models. The general framework, new results, and open problems in this space will be presented.
Speaker bio: Alex Dimakis is a professor in the electrical and computer engineering department at the University of Texas at Austin. He holds the Archie W. Straiton Endowed Faculty Fellowship in Engineering, is the co-director of the Institute for Foundations of Machine Learning, and is the associate director of the Wireless Networking and Communications Group. He received his PhD from the University of California, Berkeley, and his bachelor's degree from the National Technical University of Athens. He received several awards including the IEEE Information Theory James Massey Award, NSF Career, a Google research award, and the Eli Jury dissertation award and the joint IEEE Information Theory and Communications Society Paper Award. His research interests include information theory, coding theory and machine learning with a current focus on unsupervised learning.
Faculty host: Daniela Tuninetti, danielat@uic.edu
This presentation will not be recorded
Date posted
Nov 23, 2020
Date updated
Nov 23, 2020