Theoretical Machine Learning Seminar

Deep Generative models and Inverse Problems

Modern deep generative models like GANs, VAEs and invertible flows are showing amazing results on modeling high-dimensional distributions, especially for images. We will show how they can be used to solve inverse problems by generalizing compressed sensing beyond sparsity. We will present the general framework, new results and open problems in this space.

Date & Time

April 23, 2020 | 3:00pm – 4:30pm

Location

https://theias.zoom.us/j/384099138

Speakers

Alexandros Dimakis

Affiliation

University of Texas at Austin