Deep learning scaling is predictable, empirically
Authors
Hestness, Joel, Narang, Sharan, Ardalani, Newsha, Diamos, Gregory, Jun, Heewoo, Kianinejad, Hassan, Patwary, Md, Ali, Mostofa, Yang, Yang, Zhou, Yanqi
Venue
arXiv preprint arXiv:1712.00409
Keywords
scaling, thesis