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.