Spectral Evolution and Invariance in Linear-width Neural Networks

11 November 2022

Papers citing "Spectral Evolution and Invariance in Linear-width Neural Networks"

5 / 5 papers shown

Title
A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks Behrad Moniri Donghwan Lee Hamed Hassani Edgar Dobriban MLT 18 19 0 11 Oct 2023
Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data Yaoqing Yang Ryan Theisen Liam Hodgkinson Joseph E. Gonzalez Kannan Ramchandran Charles H. Martin Michael W. Mahoney 72 17 0 06 Feb 2022
Improved Overparametrization Bounds for Global Convergence of Stochastic Gradient Descent for Shallow Neural Networks Bartlomiej Polaczyk J. Cyranka ODL 22 3 0 28 Jan 2022
On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths Quynh N. Nguyen 25 49 0 24 Jan 2021
The large learning rate phase of deep learning: the catapult mechanism Aitor Lewkowycz Yasaman Bahri Ethan Dyer Jascha Narain Sohl-Dickstein Guy Gur-Ari ODL 150 198 0 04 Mar 2020