Denny Wu – Learning shallow neural networks in high dimensions: SGD dynamics and scaling laws
Online seminarDenny Wu is a Faculty Fellow at the Center for Data Science, New York University and the Flatiron Institute Abstract: We study the sample and time complexity of online stochastic gradient descent (SGD) in learning a two-layer neural network with M orthogonal neurons on isotropic Gaussian data. We focus on the challenging “extensive-width” regime M≫1 […]
Free
