MVA Course - Introduction to Statistical Learning

2025/2026

***Instructors:
Prof. Nicolas VAYATIS
TA : Gaëtan SERRE

***Emails:
<firstname.name/-at-/ens-paris-saclay.fr>

***Course schedule and location:

Date	Time	Room number	Instructor	Session	Topics	Material
Tuesday September 30	10:30-12:30	Oi10	N. Vayatis	Lecture #1	Chapter 1 - Optimality in binary classification Data/Objectives/Optimal elements/ERM	Slides
Tuesday October 7	10:30-12:30	1Z53	N. Vayatis	Lecture #2	Chapter 2- - Mathematical foundations (I) Probabilistic inequalities, complexity measures	Slides
Tuesday October 14	10:30-12:30	Oi10	G. Serré	Exercise session #1	Optimal elements	E-Set
Tuesday October 21	10:30-12:30	2E29	N. Vayatis	Lecture #3	Chapter 2 - Mathematical foundations (II) Regularization and stability	Slides
Tuesday October 28	10:30-12:30	1Z25	G. Serré	Exercise session #2	Inequalities, Rademacher complexity, VC dimension	E-Set
Tuesday November 4	10:30-12:30	1Z68		Partial exam - Mandatory No documents
Tuesday November 18	09:30-12:30	2E30	N. Vayatis	Lecture #4	Chapter 3 - Consistency of Machine Learning methods (I) Margin bounds and application to SVM
Tuesday November 25	10:30-12:30	1G82	G. Serré	Exercise session #3	Consistency and convergence bounds
Tuesday December 2	09:30-12:30	1G82	N. Vayatis	Lecture #5	Chapter 3 - Consistency of Machine Learning methods (II) Ensemble methods: Bagging, Random Forests, Boosting
Tuesday December 9	10:30-12:30	1Z25	N. Vayatis	Lecture #6	Chapter 3 - Consistency of Machine Learning methods (III) Neural networks, Mirror descent
Tuesday December 16	10:30-12:30	1Z25	G. Serré	Exercise session #4	Wrap-up
Tuesday January 6	10:30-12:30	1Z28		Final exam - Mandatory No documents

***Office hours (on demand):
Tuesdays 10:30am/11:30am

***Evaluation:
Partial exam on November 4 (10:30am-12:30am) - MANDATORY - No documents, no PC-tablets-phones
Final exam on January 6 (10:30am-12:30am) - MANDATORY - No documents, no PC-tablets-phones

***Grading:
Course grade = max(final ; (partial+final)/2)
*************

Chapter 1 - Optimality in statistical learning:
    From information theory to statistical learning
    The probabilistic view on numerical data,
    Optimality and the bias-variance dilemma
Chapter 2 - The mathematical foundations of statistical learning:
    Risk minimization
    Concentration inequalities
    Complexity measures
    Regularization and Stability
Chapter 3 - Theory: Consistency theorems and error bounds of learning algorithms
    Part 1 - SVM
    Part 2 - Ensemble methods: Bagging, Random Forests, Boosting

MVA Course - Introduction to Statistical Learning

Contents

Past exams

References