Topics in machine learning
Summary
Mathematical analysis of modern supervised machine learning techniques, with an emphasis on the mathematics of artificial neural networks.
Content
-
Introduction (supervised learning, risk, error decomposition, over-fitting and capacity control + cross-validation, Bayes predictor for classification and regression)
-
Differentiable programming (backpropagation algorithm) and theoretical challenges posed by modern methods (large deep neural networks)
-
Statistical analysis of Empirical Risk Minimization (learning theory, from finite number of hypotheses to Rademacher / covering numbers)
-
First-order methods for optimization (gradient descent, stochastic gradient descent).
-
Kernel methods (positive-definite kernels and Reproducing Kernel Hilbert Spaces)
-
Algorithmic regularization of gradient descent (reparameterized models, least-squares, mirror descent, logistic loss and max-margin)
-
Dynamics of large neural networks (parameterizations, neural tangent kernel and feature-learning limits, infinite width and infinite depth limits)
-
This is *not* a course for student who want to learn deep learning practice. This course is intended for the theory-inclined students who want to discover the mathematical tools that shed light on some aspects of deep learning. The course is up to date with recent theoretical research.
Keywords
Supervised learning, Machine learning, Neural networks, Optimization, Statistics
Learning Prerequisites
Required courses
Analysis, Linear Algebra, Probability and Statistics
Important concepts to start the course
-
A good knowledge of undergraduate mathematics is important.
-
Ability to code in a scientific computing programming language of your choice (e.g. Python, Matlab, Julia). The course will involve coding exercises.
-
Having followed an introductory class on machine learning is beneficial.
Teaching methods
Blackboard (or tablet) lectures
Assessment methods
Written exam
Resources
Bibliography
-"Learning theory from first principles" by Francis Bach (available online at https://www.di.ens.fr/~fbach/ltfp_book.pdf)
Moodle Link
Dans les plans d'études
- Semestre: Automne
- Forme de l'examen: Ecrit (session d'hiver)
- Matière examinée: Topics in machine learning
- Cours: 2 Heure(s) hebdo x 14 semaines
- Exercices: 2 Heure(s) hebdo x 14 semaines
- Type: optionnel
- Semestre: Automne
- Forme de l'examen: Ecrit (session d'hiver)
- Matière examinée: Topics in machine learning
- Cours: 2 Heure(s) hebdo x 14 semaines
- Exercices: 2 Heure(s) hebdo x 14 semaines
- Type: optionnel
- Semestre: Automne
- Forme de l'examen: Ecrit (session d'hiver)
- Matière examinée: Topics in machine learning
- Cours: 2 Heure(s) hebdo x 14 semaines
- Exercices: 2 Heure(s) hebdo x 14 semaines
- Type: optionnel
- Semestre: Automne
- Forme de l'examen: Ecrit (session d'hiver)
- Matière examinée: Topics in machine learning
- Cours: 2 Heure(s) hebdo x 14 semaines
- Exercices: 2 Heure(s) hebdo x 14 semaines
- Type: optionnel
- Semestre: Automne
- Forme de l'examen: Ecrit (session d'hiver)
- Matière examinée: Topics in machine learning
- Cours: 2 Heure(s) hebdo x 14 semaines
- Exercices: 2 Heure(s) hebdo x 14 semaines
- Type: optionnel
- Semestre: Automne
- Forme de l'examen: Ecrit (session d'hiver)
- Matière examinée: Topics in machine learning
- Cours: 2 Heure(s) hebdo x 14 semaines
- Exercices: 2 Heure(s) hebdo x 14 semaines
- Type: optionnel
- Semestre: Automne
- Forme de l'examen: Ecrit (session d'hiver)
- Matière examinée: Topics in machine learning
- Cours: 2 Heure(s) hebdo x 14 semaines
- Exercices: 2 Heure(s) hebdo x 14 semaines
- Type: optionnel