10 November 2021
Salle Raymond Aron, Université Paris Dauphine-PSL, Place du Maréchal de Lattre de Tassigny, 75016 Paris
Inscriptions closes / Registration closed
This is a physical workshop, no streaming is planned for this event.
Programme
08:50-09:00 Opening
Jean Ponce and Isabelle Ryl
09:00-10:40 Session I
09:00-09:20 Francis Bach (Inria, PRAIRIE), “Kernel sums of squares for optimization and beyond”
09:20-09:40 Aymeric Dieuleveut (Ecole Polytechnique, Hi! Paris), “Federated Learning with compression”
09:40-10:00 Gabriel Peyré (ENS-PSL, PRAIRIE), “Scaling optimal transport for high-dimensional Learning”
10:00-10:20 Edouard Oyallon (CNRS, SCAI), “Learning is boring: image classification with patches”
10:20-10:40 Rachel Bawden (Inria, PRAIRIE), “Handling Variation in Text with Machine Translation”
10:40-11:00 Coffee break
11:00-12:40 Session II
11:00-11:20 Thierry Poibeau (CNRS & ENS-PSL), “Poetry generation, around Oupoco”
11:20-11:40 Martial Hebert (Carnegie-Mellon University), “Robust AI”
11:40-12:00 Justin Carpentier (Inria, PRAIRIE), “Robotics – What should be really learned?”
12:00-12:20 Raphaël Porcher (Université de Paris, PRAIRIE), “Stochastic implementation of individualized treatment rules”
12:20-12:40 Nicholas Ayache (Inria, 3IA Côte-d’Azur, “AI for medical imaging – The role of models”
12:40-14:10 Lunch and posters
14:10-15:50 Session III
14:10-14:30 Alexandre Gramfort (Inria, DATAIA), “Bridging the gap between neurosciences and machine learning”
14:30-14:50 Laura Cantini (CNRS, IBENS-ENS-PSL, PRAIRIE), “Single-cell multi-modal data integration”
14:50-15:10 Jean-Baptiste Masson (Institut Pasteur, PRAIRIE), “Physics-informed Bayesian learning: from random walks to fetus morphology”
15:10-15:30 Umut Simsekli (Inria, PRAIRIE), “Towards building a heavy-tailed theory of stochastic gradient descent for deep neural networks”
15:30-15:50 Julien Mairal (Inria, MIAI), “Lucas-Kanade reloaded: End-to-end super-resolution from raw image bursts”
15:50-16:10 Coffee break
16:10-17:30 Session IV
16:10-16:30 Cordelia Schmid (Inria, PRAIRIE), “Do you see what I see? Large-scale learning from multimodal videos”
16:30-16:50 Jérôme Lang (Dauphine-PSL, PRAIRIE), “AI for collective decision making”
16:50-17:10 Jérôme Bolte (TSE School of Economics, ANITI), “Conservative calculus: a variational calculus for nonsmooth algorithmic differentiation”
17:10-17:30 Clément Royer (Dauphine-PSL, PRAIRIE), “Black-box optimization based on probabilistic properties”
17:30-18:00 Keynote and closure
Yann LeCun (New York University and Facebook AI Research), “The future is self-supervised”