Associate Professor (Reader) in Machine Learning
School of Mathematics, The University of Edinburgh
The Maxwell Institute for Mathematical Sciences
Alan Turing Institute | Bayes Centre | Gen AI Lab
School of Mathematics, Gran Sasso Science Institute
email: f dot tudisco at ed.ac.uk
I was invited to present at the SOCN (Systems, Optimization, Control and Networks) Graduate School Workshop at the University of Mons. Many thanks to Nicolas Gillis for the kind invitation!
My talk on “Low-rank geometry in deep learning” discusses network compression and efficient training through low-rank approaches, exploring how deep networks exhibit an implicit low-rank bias and presenting geometry-aware gradient descent methods with theoretical convergence guarantees.
More information about the event and my talk can be found on the SOCN website.