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.