no code implementations • 4 Oct 2023 • Gerard Ben Arous, Reza Gheissari, Jiaoyang Huang, Aukosh Jagannath
We rigorously study the joint evolution of training dynamics via stochastic gradient descent (SGD) and the spectra of empirical Hessian and gradient matrices.
no code implementations • 8 Jun 2022 • Gerard Ben Arous, Reza Gheissari, Aukosh Jagannath
We prove limit theorems for the trajectories of summary statistics (i. e., finite-dimensional functions) of SGD as the dimension goes to infinity.
no code implementations • 23 Mar 2020 • Gerard Ben Arous, Reza Gheissari, Aukosh Jagannath
Here one produces an estimator of an unknown parameter from independent samples of data by iteratively optimizing a loss function.
no code implementations • ICML 2018 • Marco Baity-Jesi, Levent Sagun, Mario Geiger, Stefano Spigler, Gerard Ben Arous, Chiara Cammarota, Yann Lecun, Matthieu Wyart, Giulio Biroli
We analyze numerically the training dynamics of deep neural networks (DNN) by using methods developed in statistical physics of glassy systems.
no code implementations • 8 Apr 2018 • Valentina Ros, Gerard Ben Arous, Giulio Biroli, Chiara Cammarota
We study rough high-dimensional landscapes in which an increasingly stronger preference for a given configuration emerges.
no code implementations • 15 Nov 2017 • Gerard Ben Arous, Song Mei, Andrea Montanari, Mihai Nica
We compute the expected number of critical points and local maxima of this objective function and show that it is exponential in the dimensions $n$, and give exact formulas for the exponential growth rate.
no code implementations • 20 Dec 2014 • Levent Sagun, V. Ugur Guney, Gerard Ben Arous, Yann Lecun
Finding minima of a real valued non-convex function over a high dimensional space is a major challenge in science.