Frugality in machine learning: Sparsity, a value for the future? Sparse vectors and sparse matrices play a transerve role in signal and image processing: they have led to succesful approaches efficiently addressing tasks as diverse as data compression, fast transforms, signal denoising and source separation, or more generally inverse problems. To what extent can the …
Category: Talk
Invited talk, MAP5, Paris, May 17th 2024
Frugality in machine learning: Sparsity, a value for the future? Sparse vectors and sparse matrices play a transerve role in signal and image processing: they have led to succesful approaches efficiently addressing tasks as diverse as data compression, fast transforms, signal denoising and source separation, or more generally inverse problems. To what extent can the …
Invited talk, Math Machine Learning seminar MPI MIS + UCLA, online, May 16, 2024
‘Conservation Laws for Gradient Flows’ Understanding the geometric properties of gradient descent dynamics isa key ingredient in deciphering the recent success of very largemachine learning models. A striking observation is that trainedover-parameterized models retain some properties of the optimizationinitialization. This “implicit bias” is believed to be responsible forsome favorable properties of the trained models and …
Invited talk @RWTH Sparsity and Singular Structures, Aachen, 26-29 February 2024
https://sfb1481.rwth-aachen.de/symposium24/programme
Invited talk at JRAF, Grenoble, 13-14 December 2023
https://jraf-2023.sciencesconf.org/
Invited Talk @DIPOpt workshop, Nov 29th 2023
http://perso.ens-lyon.fr/nelly.pustelnik/DIPOpt/
Exposé à la journée d’étude “Quelle IA pour 2030?” du projet AILyS
https://www.ens-lyon.fr/evenement/recherche/quelle-ia-pour-2030-le-projet-ailys
Invited talk @ Stéphane Mallat’s 60
Invited talk at the workshop “A Multiscale tour of Harmonic Analysis and Machine Learning” – celebrating Stéphane Mallat’s 60th birthday – @Institut_IHES, “Rapture of the deep : Highs and lows of Sparsity in a world of depth”, April 21st 2023
Data-Science Colloquium of the @ENS Paris
Seminar at the Data-Science Colloquium of the @ENS Paris “Rapture of the deep : Highs and lows of Sparsity in a world of depth”, February 2nd 2023, https://data-ens.github.io/past/
Seminar @IRIT, Nov 28th
Seminar @ENSEEIHT “Rapture of the deep : Highs and lows of Sparsity in a world of depth”, https://www.irit.fr/departement/signaux-images/sc/