activity
20182026
most citedsignSGD with Majority Vote is Communication Efficient And Fault Tolerant

124 citations · 158 across the 22 of their papers we have counts for

collaborators
Showing 2021Show all

2 papers · 1 filter

cs.LG2021★ 10 cited

ZerO Initialization: Initializing Neural Networks with only Zeros and Ones

Jiawei Zhao, Florian Schäfer, Anima Anandkumar

Deep neural networks are usually initialized with random weights, with adequately selected initial variance to ensure stable signal propagation during training. However, selecting…

cs.LG2021

LNS-Madam: Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update

Jiawei Zhao, Steve Dai, Rangharajan Venkatesan +6

Representing deep neural networks (DNNs) in low-precision is a promising approach to enable efficient acceleration and memory reduction. Previous methods that train DNNs in low-pre…