Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks

20 September 2021

Papers citing "Deformed semicircle law and concentration of nonlinear random matrices for ultra-wide neural networks"

7 / 7 papers shown

Title
How Spurious Features Are Memorized: Precise Analysis for Random and NTK Features Simone Bombari Marco Mondelli AAML 19 4 0 20 May 2023
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels Simone Bombari Shayan Kiyani Marco Mondelli AAML 28 10 0 03 Feb 2023
High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation Jimmy Ba Murat A. Erdogdu Taiji Suzuki Zhichao Wang Denny Wu Greg Yang MLT 31 121 0 03 May 2022
Concentration of Random Feature Matrices in High-Dimensions Zhijun Chen Hayden Schaeffer Rachel A. Ward 20 6 0 14 Apr 2022
On the Proof of Global Convergence of Gradient Descent for Deep ReLU Networks with Linear Widths Quynh N. Nguyen 33 49 0 24 Jan 2021
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks Lechao Xiao Yasaman Bahri Jascha Narain Sohl-Dickstein S. Schoenholz Jeffrey Pennington 220 348 0 14 Jun 2018
Sharp analysis of low-rank kernel matrix approximations Francis R. Bach 80 277 0 09 Aug 2012