Goals

Sparsity and convexity are ubiquitous notions in Machine Learning and Statistics. In this course, we study the mathematical foundations of some powerful methods based on convex relaxation: L1-regularisation techniques in Statistics and Signal Processing. These approaches turned to be Semi-Definite representable (SDP) and hence tractable in practice. The theoretical part of the course will focus on the guarantees of these algorithms under the sparsity assumption. The practical part of this course will present the standard solvers of these learning problems.

Programme

  1. Optimisation convexe et méthodes d'accélération
  2. Algorithmes pour la regression parcimonieuse en grande dimension
  3. Guaranties théoriques en grande dimension
  4. Apprentissage compressé
Course
18h
 

Responsibles

  • Laurent SEPPECHER
  • Yohann DE CASTRO

Language

French

Keywords

L1-regularization; Sparse Models; Optimization;