Introduction to Machine Learning

Francis Bach, Lena´c Chizat

Mastere M2 ICFP, 2019/2020

 

Mandatory registration

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



Summary 

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.



Dates


Classes will be held in the room L367 (third floor, ENS, 24 rue Lhomond), Friday morning from 9am to 12pm when no practical sessions, and to 12.30pm when there are practical sessions. Class notes will be made available. Practical sessions will be held on laptops with Python 3 and Jupyter notebooks (please make sure to install it before January 17, and run this script).

Lecturer Date Topics Class notes / code
FB 10 January Introduction to supervised learning (loss, risk, over-fitting and capacity control + cross-validation, Bayes predictor for classification and regression lecture1.pdf
LC 17 January Least-squares regression (all aspects, from linear algebra to statistical guarantees and L2 regularization + practical session) lecture2.pdf
TD1.ipynb
mnist_digits.mat

FB 24 January Statistical ML without optimization (learning theory, from finite number of hypothesis to Rademacher / covering numbers)
FB 31 January Local averaging techniques (K-nearest neighbor, Nadaraya-Watson regression: algorithms + statistical analysis + practical session)
LC 7 February Empirical risk minimization (logistic regression, loss-based supervised learning, probabilistic interpretation through maximum likelihood)
LC 14 February Convex optimization (gradient descent + nonsmooth + stochastic versions + practical session (logistic regression))

21 February Holidays
FB 28 February Model selection (feature selection, L1 regularization and high-dimensional inference + practical session)
FB 6 March Kernels (positive-definite kernels and reproducing kernel Hilbert spaces + practical session)
LC 13 March Neural networks (from one-hidden layer to deep networks + practical session)
LC 20 March Unsupervised learning (K-means and PCA (potentially with kernels) + mixture models (potentially EM) + practical session)

27 March Review

3 April Exam



Evaluation

Evaluation: practical sessions to finish at home + written in-class exam