Introduction to Machine Learning

Francis Bach, Lena´c Chizat

Mastere M2 ICFP, 2020/2021


Mandatory registration

The class will be taught in French or English, depending on attendance (all slides and class notes are in English).


Statistical machine learning is a growing discipline at the intersection of computer science and applied mathematics (probability / statistics, optimization, etc.) and which increasingly plays an important role in many other scientific disciplines.

Unlike a course on traditional statistics, statistical machine learning is particularly focused on the analysis of data in high dimension, as well as the efficiency of algorithms to process the large amount of data encountered in multiple application areas such as image or sound analysis, natural language processing, bioinformatics or finance.

The objective of this class is to present the main theories and algorithms in statistical machine learning, with simple proofs of the most important results. The practical sessions will lead to simple implementations of the algorithms seen in class.


Given the sanitary situations, classes will most probably held online on Friday morning from 9am to 12pm. Detailed class notes will be made available before class and lecturers will go through them. Practical sessions will be done at home.

Please send the practical sessions (one jupyter notebook .ipynb with cells containing either text or runnable code) to with the subject [PSn] with n being the number of the practical session (no acknowledgements will be sent back).

Lecturer Date Topics Class notes / code
LC 15 January Introduction to supervised learning (loss, risk, over-fitting and capacity control + cross-validation, Bayes predictor for classification and regression
FB 22 January Least-squares regression (all aspects, from linear algebra to statistical guarantees and L2 regularization + practical session)
Practical session 1, due February 7, 2020

LC 29 January Statistical ML without optimization (learning theory, from finite number of hypothesis to Rademacher / covering numbers)
FB 5 February Local averaging techniques (K-nearest neighbor, Nadaraya-Watson regression: algorithms + statistical analysis + practical session)
LC 12 February Empirical risk minimization (logistic regression, loss-based supervised learning, probabilistic interpretation through maximum likelihood)
FB 19 February Convex optimization (gradient descent + nonsmooth + stochastic versions + practical session (logistic regression))

26 February Holidays
LC 5 March
Model selection (feature selection, L1 regularization and high-dimensional inference + practical session)
FB 12 March Kernels (positive-definite kernels and reproducing kernel Hilbert spaces)
LC 19 March Neural networks (from one-hidden layer to deep networks + practical session)
FB 26 March Review

2 April Exam


Evaluation: practical sessions to do at home + written take-home exam