Coursebooks 2017-2018

PDF
 

Working Group in High-Dimensional Statistics

MATH-692

Lecturer(s) :

Morgenthaler Stephan

Language:

English

Summary

This course will cover topics related to high-dimensional statistics, that is, situations where the number of unknowns is of much larger order than sample size. This includes discussion of the sparse models (Lasso), multiple testing, supervised classification and graphical models.

Content

In this course we will start with the analysis of high-dimensional data in the context of linear models and discuss the subsequent evolution of the theory.

The following topics will be covered: Lasso and related methods (computational and theoretical aspects), application to generalized linear models, additive models, p-values and multiple testing, graphical models, boosting and classification.

Keywords

High-dimensional statistics, Lasso, model selection, multiple testing

Learning Prerequisites

Required courses

Probability theory, statistical theory, an advanced statistics course

Recommended courses

Statistical learning

Learning Outcomes

By the end of the course, the student must be able to:

Resources

Bibliography

Statistics for high-dimensional data (P. Buehlmann, S. van de Geer, Springer), Introduction to high-dimensional statistics (Ch. Giraud, CRC Press)

Ressources en bibliothèque

In the programs

    • Semester
    • Exam form
       Oral
    • Credits
      2
    • Subject examined
      Working Group in High-Dimensional Statistics
    • Lecture
      14 Hour(s)
    • Practical work
      14 Hour(s)

Reference week

 
      Lecture
      Exercise, TP
      Project, other

legend

  • Autumn semester
  • Winter sessions
  • Spring semester
  • Summer sessions
  • Lecture in French
  • Lecture in English
  • Lecture in German