Talk on Phase Retrieval: computational imaging in the machine learning era

 A talk on

by Jonathan Dong, Biomedical Imaging Group, Ecole polytechnique federale de Lausanne, Switzerland

Venue: B303, Electrical Engineering Department (second floor), IISc

Date: April 21, 2025; Time: 4 PM (Coffee will be served at 3.45 PM)

Host: Prof. Chandra Sekhar Seelamantula (EE)

Phase retrieval is a fundamental nonlinear inverse problem that appears across a wide range of computational imaging applications, from X-ray and electron ptychography to phase imaging in optical microscopy. Because it is often addressed through nonlinear optimization techniques, it has deep links with modern machine learning theory. In this talk, I will provide a unified overview of phase retrieval models and algorithms, highlighting the connections between different applications. I will also discuss recent theoretical insights on reconstruction guarantees derived from random matrix theory. Finally, we’ll explore practical implementations, and I’ll share how these extend to our recent work on differentiable physical models and open-source computational imaging tools.

Jonathan Dong is an SNF Ambizione Fellow with Prof. Michael Unser at the Biomedical Imaging Group, EPFL, Lausanne, Switzerland. He received his Ph.D. degree in Physics in 2020 from Ecole Normale Supérieure in Paris, France. His research interests include nonlinear inverse problems and computational imaging, with a focus on physics-based models, reconstruction algorithms, and statistical analysis methods.