LMS Workshop: Variational Methods Meet Machine Learning


18 September, 2017


University of Cambridge
Centre for Mathematical Sciences



This workshop is sponsored by Cantab Capital Institute for the Mathematics of Information and the London Mathematical Society.

A picture of CMS Cambridge.

CCIMI logo.   LMS logo.


Only recently have machine learning algorithms came into focus in the inverse problems and more general computational mathematics communities. The early publications include both attempts to provide theoretical underpinning of the methods (e.g. analysis of deep network frameworks both more general as well as through construction of dedicated "interpretable" layers, or analysis of stochastic gradient methods), as well as proposals of how the methods could be used in the context of inverse problems (e.g. unsupervised learning of parameters of variational models or training deep neural networks to provide approximate solutions of variational problems). The goal of this one day workshop is to bring together researchers working on variational methods in inverse problems and machine learning to identify the parallels between the fields as well as discover new research avenues. This will be facilitated by two discussion sessions.

Invited Speakers


Please click on the titles for abstracts where available.

10:00 - 10:30Registration
10:25 - 10:30 Welcome/Opening Remarks
10:30 - 11:00 Thomas PockLearning better models for inverse problems in imaging
11:05 - 11:35 Andreas HauptmannModel based learning for accelerated, limited-view 3D photoacoustic tomography
11:35 - 12:05 Coffee break
12:05 - 12:35Jonas AdlerLearned iterative reconstruction schemes, theory and practice
12:40 - 13:10Christian EtmannRegularisation of neural networks with input saliencies
13:15 - 13:30 Morning discussion
13:30 - 14:30 Lunch
14:30 - 15:00Michael HintermüllerBilevel optimization and some "parameter learning" applications in image processing
15:05 - 15:35Joana GrahLearning filter functions in regularisers by minimising quotients
15:35 - 16:05Coffee break
16:05 - 16:35 Mila NikolovaFast solvers for approximating inconsistent systems of linear inequalities
16:40 - 17:00Afternoon discussion


To register for the workshop please email Marta Betcke: [at]ucl.ac.uk. There is no fee, but we would like to know if you are coming for planning purposes. Also, if you would like to participate in the poster session, which will take place during lunch, please include a proposed title and abstract for your poster in the email.