Follow
Abhinav Venigalla
Abhinav Venigalla
Machine Learning Researcher, Cerebras Systems
Verified email at cerebras.net
Title
Cited by
Cited by
Year
Pipelined backpropagation at scale: training large models without batches
A Kosson, V Chiley, A Venigalla, J Hestness, U Koster
Proceedings of Machine Learning and Systems 3, 479-501, 2021
262021
Representation range needs for 16-bit neural network training
V Popescu, A Venigalla, D Wu, R Schreiber
arXiv preprint arXiv:2103.15940, 2021
22021
Adaptive braking for mitigating gradient delay
A Venigalla, A Kosson, V Chiley, U Köster
arXiv preprint arXiv:2007.01397, 2020
22020
Strongly-transferring memorized examples in deep neural networks
AS Venigalla
Massachusetts Institute of Technology, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–4