86 citations · 286 across the 17 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2021★ 12 cited
Deep Extrapolation for Attribute-Enhanced Generation
Alvin Chan, Ali Madani, Ben Krause +1
Attribute extrapolation in sample generation is challenging for deep neural networks operating beyond the training distribution. We formulate a new task for extrapolation in sequen…
cs.LG2020★ 13 cited
Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width
Yu Bai, Ben Krause, Huan Wang +2
We propose \emph{Taylorized training} as an initiative towards better understanding neural network training at finite width. Taylorized training involves training the -th order…
cs.LG2019★ 33 cited
Dynamic Evaluation of Transformer Language Models
Ben Krause, Emmanuel Kahembwe, Iain Murray +1
This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation. Transformers use stacked layers…