Optimisation 2

  • Voir la page en français

    In brief

  • Code : N8EN07A

Objectives

Machine learning application often lead to optimisation problems of a composite nature: a typical fit-to-data term is penalized so as to enforce some geometrical properties in the solution. Typical properties include sparcity, low rank in matrices. Such problems are often non-differentiable but convex. We review the most popular sub-gradient based methods for solving such problems, insisting on the convergence properties and the complexity of such methods. We will also focus on efficient implementation of such methods on image processing applications. Finally, we will develop in the SPARK software a movie recommendation system.

Needed prerequisite

Basic course on linear algebra, Basic algorithms for unconstrained optimisation

Session 1 ou session unique - Contrôle des connaissances

ModalitéNatureCoefficientRemarques
CT (contrôle terminal) Oral/Ecrit50%Examn Optimisation 2
CC (contrôle continu) Travaux Pratiques50%TP-Optimisation 2

Session 2 - Contrôle des connaissances

ModalitéNatureCoefficientRemarques
CT (contrôle terminal) Oral/Ecrit50%Examn Optimisation 2
CC (contrôle continu) Travaux Pratiques50%TP-Optimisation 2

Contact(s)

GRATTON SERGE

Contact

The National Institute of Electrical engineering, Electronics, Computer science,Fluid mechanics & Telecommunications and Networks

2, rue Charles Camichel - BP 7122
31071 Toulouse Cedex 7, France

+33 (0)5 34 32 20 00

Certifications

  • Logo MENESR
  • Logo UTFTMP
  • Logo INP
  • Logo INPT
  • Logo Mines télécoms
  • Logo CTI
  • Logo CDEFI
  • Logo midisup