activity
20202026
most citedAn initial alignment between neural network and target is needed for gradient descent to learn

2 citations · 3 across the 8 of their papers we have counts for

collaborators
Showing 2022Show all

2 papers · 1 filter

cs.IT2022

Optimal list decoding from noisy entropy inequality

Jan Hązła

A noisy entropy inequality for boolean functions by Samorodnitsky is applied to binary codes. It is shown that a binary code that achieves capacity on the binary erasure channel ad…

cs.LG2022★ 2 cited

An initial alignment between neural network and target is needed for gradient descent to learn

Emmanuel Abbe, Elisabetta Cornacchia, Jan Hązła +1

This paper introduces the notion of ``Initial Alignment'' (INAL) between a neural network at initialization and a target function. It is proved that if a network and a Boolean targ…