Schedule:

Monday 16

  • 14:00 - 14:30 : Welcome and Foreword
  • 14:30 - 16:00 : Approximation of multivariate functions (1/4), Albert Cohen
  • 16:00 - 16:30 : Coffee break
  • 16:30 - 17:30 : Approximation of multivariate functions (2/4), Albert Cohen
  • 17:45 - 19:15 : Cocktail

Tuesday 17

  • 09:00 - 10:30 : Approximation of multivariate functions (3/4), Albert Cohen
  • 10:30 - 11:00 : Coffee break
  • 11:00 - 12:00 : Approximation of multivariate functions (4/4), Albert Cohen
  • 12:00 - 14:00 : Lunch break
  • 14:00 - 16:00 : Approximation with Hierarchical Low Rank Tensors (1/3), Lars Grasedyck
  • 16:00 - 16:30 : Coffee break
  • 16:30 - 17:30 : Approximation with Hierarchical Low Rank Tensors (2/3), Lars Grasedyck

Wednesday 18

  • 08:30 - 10:30 : Approximation with Hierarchical Low Rank Tensors (3/3), Lars Grasedyck  
  • 10:30 - 11:00 : Coffee break
  • 11:00 - 12:00 : Approximation theory of deep neural networks (1/3), Philipp Petersen
  • 12:00 - 14:00 : Lunch break
  • 14:00 - 16:00 : Approximation theory of deep neural networks (2/3), Philipp Petersen
  • 16:00 - 16:30 : Coffee break
  • 16:30 - 17:30 : Approximation lower bounds in L^p norm with applications to feedforward neural networks, Sébastien Gerchinovitz
  • 19h15 : Gala dinner,  Restaurant A Cantina, 28 Rue Kervégan, 44000 Nantes, link

Thursday 19

  • 08:30 - 10:30 : Approximation with Hierarchical Low Rank Tensors (practical session 1/2), Sebastian Krämer
  • 10:30 - 11:00 : Coffee break
  • 11:00 - 12:00 : Statistical theory of deep learning (1/2), Sophie Langer
  • 12:00 - 14:00 : Lunch break
  • 14:00 - 16:00 : Statistical theory of deep learning (2/2), Sophie Langer
  • 16:00 - 16:30 : Coffee break
  • 16:30 - 17:30 : Benign overfitting : analysis of the generalisation paradox, Stéphane Chrétien

Friday 20

  • 08:30 - 10:30 : Approximation theory of deep neural networks (3/3), Philipp Petersen
  • 10:30 - 11:00 : Coffee break
  • 11:00 - 13:00 : Approximation with Hierarchical Low Rank Tensors (practical session 2/2), Sebastian Krämer
  • 13:00 - 14:30 : Lunch

 

 Abstracts

  • Course 1: Albert Cohen, Approximation of multivariate functions: reduced modeling and recovery from uncomplete 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, 
  •  Lecture 1: Sébastien Gerchinovitz, Approximation lower bounds in L^p norm, with applications to feedforward neural networks
  •  Lecture 2: Stéphane Chrétien, Benign overfitting : analysis of the generalisation paradox,

 

Slides

Practical sessions