Optimization for Machine Learning
M2 IASD, Université Paris Dauphine-PSL, 2025-2026
Aim of the course
Study the main optimization techniques used in machine learning and data science, as well as their underlying principles.
Course project (tentative deadline: December 19, 2025)
Assignment (Version Oct. 24)
PDF
Course material
Exercises (V4.1, Nov. 5)
PDF
Session 1: Basics of optimization
Intro slides
PDF
Virtual board
PDF
Backup slides (with material not covered in class)
PDF
Session 2: Differentiation
Virtual board
PDF
Notebook (without solutions)
ZIP
Notebook (with solutions)
ZIP
Session 3: Gradient methods
Virtual board (corrected version Oct. 10)
PDF
Notebook (without solutions)
ZIP
Notebook (with solutions)
ZIP
Session 4: Nonconvex and nonsmooth optimization
Virtual board
PDF
Illustration notebook
ZIP
Session 5: Proximal methods
Virtual board
PDF
Illustration notebook
ZIP
Session 6: Stochastic gradient
Virtual board
PDF
Notebook (without solutions)
ZIP
Notebook (with solutions)
ZIP
Session 7: Advanced stochastic methods
Virtual board
PDF
Illustration notebook
ZIP
Materials on this page are available under Creative Commons
CC BY-NC 4.0 license.
La version française de cette page se trouve
ici.