Non-Linear and High Dimensional Inference

3-7 October 2022 - IHP, Paris

In statistical learning and modern statistics, it is usually assumed that although data is observed in very high dimension, it actually live on — or near — a geometric structure of low dimension. The knowledge of such a low-complexity structure is of fundamental importance to improve both theoretical and computational aspects of a learning procedures.

Invited Speakers

• Peter Bartlett (UC Berkeley)
• Mikhail Belkin (UC San Diego)
• Clément Bérenfeld (CEREMADE, Dauphine)
• Gilles Blanchard (LMO, Orsay)
• Alexander Cloninger (UC San Diego)
• Adeline Fermanian (Mines ParisTech)
• Damien Garreau (U Côte d'Azur)
• John Harlim (Penn State)
• Christian Hennig (Bologna)
• Claire Lacour (Paris-Est, Marne-la-Vallée)
• Sophie Langer (TU Darmstadt)
• Didong Li (Princeton)
• Marina Meila (University of Washington)
• Franck Picard (ENS Lyon)
• Judith Rousseau (Oxford)
• Botond Szabó (Bocconi)
• Johannes Schmidt-Hieber (Twente)
• Vasiliki Velona (Hebrew University of Jerusalem)
• Nicolas Verzelen (Inrae Montpellier)