Bilevel Learning for Inverse Problems

Wed, Jul 7, 2021, 12:00 pm
Location: 
https://zoom.us/j/91342019907
Speaker(s): 

The One World Seminar on The Mathematics of Machine Learning

Date: Wednesday, July 7, 2021

Time: 12 noon EST (5PM BST / 6PM CEST / 9AM PDT / 10AM MDT / 11AM CDT). You can join using the zoom link: https://zoom.us/j/91342019907  (the link will also be visible on the website just before the talk).

Speaker:  Matthias Ehrhardt (University of Bath)

https://www.oneworldml.org/home

Title: Bilevel Learning for Inverse Problems

Abstract: Variational regularization techniques are dominant in the field of inverse problems. A drawback of these techniques is that they are dependent on a number of parameters which have to be set by the user. This issue can be approached by machine learning where we estimate these parameters from data. This is known as "Bilevel Learning" and has been successfully applied to many tasks, some as small-dimensional as learning a regularization parameter, others as high-dimensional as learning a sampling pattern in MRI. While mathematically appealing this strategy leads to a nested optimization problem which is computationally difficult to handle. In this talk we discuss several applications of bilevel learning for imaging as well as new computational approaches. There are quite a few open problems in this relatively recent field of study, some of which I will highlight along the way.