87 citations · 104 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021
Multilayer Lookahead: a Nested Version of Lookahead
Denys Pushkin, Luis Barba
In recent years, SGD and its variants have become the standard tool to train Deep Neural Networks. In this paper, we focus on the recently proposed variant Lookahead, which improve…
cs.LG2020★ 87 cited
Dynamic Model Pruning with Feedback
Tao Lin, Sebastian U. Stich, Luis Barba +2
Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased…