High-Dimensional Non-Convex Landscapes and Gradient Descent Dynamics
arXiv:2308.03754
Abstract
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.
Lectures given by G. Biroli at the 2022 Les Houches Summer School "Statistical Physics and Machine Learning"