activity
20162021
most citedOn Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima

571 citations · 858 across the 10 of their papers we have counts for

collaborators
Showing cs.MSShow all

1 paper · 1 filter

cs.MS2019

Leveraging the bfloat16 Artificial Intelligence Datatype For Higher-Precision Computations

Greg Henry, Ping Tak Peter Tang, Alexander Heinecke

In recent years fused-multiply-add (FMA) units with lower-precision multiplications and higher-precision accumulation have proven useful in machine learning/artificial intelligence…