Past Event: Babuška Forum

Deep generative models and inverse problems

Alex Dimakis, Professor, ECE department, UT Austin

Abstract

**This seminar will be presented LIVE in POB 6.304.  It will also be streamed live via Zoom.**

Modern deep generative models like GANs, VAEs, invertible flows and Score-based models are demonstrating excellent performance in representing high-dimensional distributions, especially for images. We will show how they can be used to solve inverse problems like denoising, filling missing data, and recovery from linear projections. We generalize compressed sensing theory beyond sparsity, extending Restricted Isometries to sets created by deep generative models. Our recent results include establishing theoretical results for Langevin sampling from full-dimensional generative models and training the first generative model for MRI data, also achieves state of the art performance for accelerating MR imaging. 

Biography

Alex Dimakis is a Professor at the ECE department at UT Austin and the co-director of the National AI Institute on the Foundations of Machine Learning (IFML). He received his Ph.D. from UC Berkeley and the Diploma degree from the National Technical University of Athens. He received several awards including the James Massey Award, NSF Career, a Google research award, the Eli Jury dissertation award, the 2012 joint Information Theory and Communications Society Best Paper Award and the 2010 IEEE ComSoc Data Storage Best paper award. His research interests include information theory, coding theory and machine learning.