Neural gradients are near-lognormal: improved quantized and sparse training

15 June 2020

Papers citing "Neural gradients are near-lognormal: improved quantized and sparse training"

4 / 4 papers shown

Title
Bimodal Distributed Binarized Neural Networks T. Rozen Moshe Kimhi Brian Chmiel A. Mendelson Chaim Baskin MQ 64 4 0 05 Apr 2022
Minimum Variance Unbiased N:M Sparsity for the Neural Gradients Brian Chmiel Itay Hubara Ron Banner Daniel Soudry 23 10 0 21 Mar 2022
Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats Brian Chmiel Ron Banner Elad Hoffer Hilla Ben Yaacov Daniel Soudry MQ 33 23 0 19 Dec 2021
What is the State of Neural Network Pruning? Davis W. Blalock Jose Javier Gonzalez Ortiz Jonathan Frankle John Guttag 191 1,032 0 06 Mar 2020