MVA Course - Introduction to Statistical Learning

2017/2018

Instructor: Nicolas VAYATIS
Teaching assistant: Xavier FONTAINE

<name/-at-/cmla.ens-cachan.fr>

 **************
Room: Condorcet

Date Time Instructor Session Topics Files/Readings
Tuesday October 3 11:00-13:00 N. Vayatis Lecture #1 Chapter 1 - Modeling aspects
classification data and classification problem
Slides
Tuesday October 10 08:45-10:45 N. Vayatis Lecture #2 Chapter 1 - Modeling aspects
Other problems: convex risk minimization, preference learning, scoring
Slides
Tuesday October 17
08:00-10:00 X. Fontaine Exercise session #1 Optimal elements and excess risk bounds Sheet
Tuesday October 24
08:45-10:45 N. Vayatis Lecture #3 Chapter 2 - Mathematical tools
Probabilistic inequalities, complexity measures
Slides
Tuesday October 31 08:45-10:45 X. Fontaine Exercise session #2 Inequalities, Rademacher complexity, VC dimension Sheet
Tuesday November 7
08:45-10:45
Partial exam - Mandatory

Tuesday November 14
08:45-10:45 N. Vayatis Lecture #4 Chapter 3 - Consistency of Machine Learning methods
SVM and Boosting
Slides
Tuesday November 21
08:45-10:45 N. Vayatis Lecture #5 Chapter 3 - Consistency of Machine Learning methods
Neural networks, bagging, random forests
Slides
Tuesday November 28 08:45-10:45 X. Fontaine Exercise session #3 Consistency and convergence bounds Sheet
Tuesday December 5
08:45-10:45 N. Vayatis Lecture #6 Chapter 4 - Advanced topics
Multiclass classification, ranking, ...
Slides
Tuesday December 12 08:45-10:45 X. Fontaine Exercise session #4 Wrap-up Sheet
Tuesday December 19
08:45-10:45
Final exam



Office hours: Tuesdays 1pm/2pm - Laplace 126
**************
Partial exam on November 7 (am) - MANDATORY
Final exam on December 19 (am) - OPTION 1
Project presentations on January 9 (am) - OPTION 2
**************

Contents

Chapter 1 - Modeling aspects: Data, decision, risk, optimality
Chapter 2 - Tools: Concentration inequalities and complexity measures
Chapter 3 - Theory: Consistency and error bounds of learning algorithms

Chapter 4 - Advanced topics: multiclass classification, ranking, link prediction, ...

Lecture Notes

Link

Past exams

Final exam 2016 / Partial exam 2016 / Final exam 2015 / Partial exam 2015 / Final exam 2014 / Partial exam 2014 /


References