most citedSpectral alignment of stochastic gradient descent for high-dimensional classification tasks

2 citations · 2 across the 1 of their papers we have counts for

collaborators

2 papers

math.ST2025

Local geometry of high-dimensional mixture models: Effective spectral theory and dynamical transitions

Gerard Ben Arous, Reza Gheissari, Jiaoyang Huang +1

We study the local geometry of empirical risks in high dimensions via the spectral theory of their Hessian and information matrices. We focus on settings where the data, $(Y_\ell)_…

cs.LG2023★ 2 cited

Spectral alignment of stochastic gradient descent for high-dimensional classification tasks

Gerard Ben Arous, Reza Gheissari, Jiaoyang Huang +1

We rigorously study the relation between the training dynamics via stochastic gradient descent (SGD) and the spectra of empirical Hessian and gradient matrices. We prove that in tw…