Martin Benning - Deep learning as optimal control problems
|Starts:||12:00 11 Feb 2020|
|Ends:||13:00 11 Feb 2020|
|What is it:||Seminar|
|Organiser:||Department of Mathematics|
|Who is it for:||University staff, External researchers, Current University students|
|Speaker:||Dr Martin Benning|
Join us for this research seminar, part of the SQUIDS (Statistics, quantification of uncertainty, inverse problems and data science) seminar series.
Abstract: We consider recent works where deep neural networks have been interpreted as discretisations of an optimal control problem subject to an ordinary differential equation constraint. We review the first order conditions for optimality, and the conditions ensuring optimality after discretisation. This leads to a class of algorithms for solving the discrete optimal control problem which guarantee that the corresponding discrete necessary conditions for optimality are fulfilled. The differential equation setting lends itself to learning additional parameters such as the time discretisation. We explore this extension alongside natural constraints (e.g. time steps lying in a simplex) and compare these deep learning algorithms numerically in terms of induced flow and generalisation ability. We conclude by addressing the interpretation of this extension as iterative regularisation methods for inverse problems.
This is joint work with Elena Celledoni, Matthias J. Ehrhardt, Brynjulf Owren and Carola-Bibiane Schönlieb.
Dr Martin Benning
Role: Lecturer in Optimisation/Machine Learning
Organisation: Queen Mary University of London
Travel and Contact Information
Frank Adams 1
Alan Turing Building