Centrale Nantes hosting the research school: High-dimensional approximation and Deep Learning

This research school addresses the mathematical foundations of high-dimensional approximation and statistical learning, with particular attention to nonlinear approximation, model reduction, tensors and neural networks.

The research school is designed for PhD students, young researchers and confirmed researchers interested in these topics.

The school will feature four courses given by experts in the mathematics of approximation and learning:
 

• Course 1: Albert Cohen, Approximation of multivariate functions: reduced modeling and recovery from incomplete measurements
• Course 2: Lars Grasedyck, Approximation with Hierarchical Low Rank Tensors
• Course 3: Sophie Langer, On the statistical theory of deep learning
• Course 4: Philipp Petersen, Approximation theory of deep neural networks

Guest speakers will complement courses on recent advances in learning algorithms and approximation theory of neural networks.
 

• Sébastien Gerchinovitz, Approximation lower bounds in L^p norm, with applications to feedforward neural networks
• Stéphane Chrétien, TBA

► Learn more about the event
 

This event is organised in partnership with Centrale Nantes, the Jean Leray Mathematical Institute, Nantes University, the CNRS, the French statistics society, the applied and industrial mathematics society and the Mascot-num research group.