CSE Community Seminar
September 13, 2024, 12 PM
Conference Room 45-432 in Building 45
Recovery phenomena with symmetric autoencoders
Laurent Demanet
Professor of Applied Mathematics,
Department of Mathematics at MIT
Abstract:
Can we find the solution of a PDE we have never seen, if we collect enough solutions of nearby equations? Is it possible to guess what a scene in an image would look like if the picture was taken from a different angle? Would it sound like you if an AI generated a deepfake of your voice? These questions fit in a common mathematical framework of estimation of low-dimensional latent processes under maps of controlled complexity. I will explain how ML has advanced to answer these questions, possibly with mathematical guarantees in the form of recovery principles à la compressed sensing. Joint work with Pawan Bharadwaj, Matt Li, and Borjan Geshkovski.
September 13, 2024, CSE Community Seminar
Laurent Demanet
Professor of Applied Mathematics,
Department of Mathematics, MIT.