Latest


2023.10.23: Second notebook online, virtual board for lecture 3.
2023.10.19: Virtual board for lecture 2 online.
2023.10.12: Virtual board for lecture 1 online.
2023.10.11: Lecture notes+first notebook online.
2023.10.09: The lecture webpage is online.

Lecturer

Clément Royer
clement.royer@lamsade.dauphine.fr

Back to the general teaching page

Stochastic gradient methods

Optimization for Machine Learning

M2 IASD/MASH, Université Paris Dauphine-PSL, 2023-2024


Program

     In these three lectures, we will study the major concepts behind stochastic optimization techniques and their relevance in machine learning and data science. We will discuss both the theoretical foundations supporting these methods and the challenges posed by their implementation.

Schedule

     Lecture 1/3 (10/12) Introduction to stochastic gradient.
     Lecture 2/3 (10/19) Analysis and implementation of stochastic gradient.
     Lecture 3/3 (10/23) Advanced aspects in stochastic gradient.

Course material

     Lecture notes PDF
     Python notebook on bases of stochastic gradient [Sources]
     Python notebook on advanced aspects [Sources]

Lecture boards

     Virtual board for the first session PDF
     Virtual board for the second session PDF
     Virtual board for the third session PDF


Materials on this page are available under Creative Commons CC BY-NC 4.0 license.
La version française de cette page se trouve ici.