High-dimensional non-convex landscapes and gradient descent dynamics
Résumé
In these lecture notes we present different methods and concepts developed in statistical physics to analyze gradient descent dynamics in high-dimensional non-convex landscapes. Our aim is to show how approaches developed in physics, mainly statistical physics of disordered systems, can be used to tackle open questions on high-dimensional dynamics in machine learning.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |