activity
20222026
most citedBeyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels

2 citations · 4 across the 9 of their papers we have counts for

collaborators
Showing cs.ITShow all

1 paper · 1 filter

cs.IT2022

Sharp asymptotics on the compression of two-layer neural networks

Mohammad Hossein Amani, Simone Bombari, Marco Mondelli +2

In this paper, we study the compression of a target two-layer neural network with N nodes into a compressed network with M<N nodes. More precisely, we consider the setting in which…