75 citations · 303 across the 30 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023
PaReprop: Fast Parallelized Reversible Backpropagation
Tyler Zhu, Karttikeya Mangalam
The growing size of datasets and deep learning models has made faster and memory-efficient training crucial. Reversible transformers have recently been introduced as an exciting ne…
cs.LG2018★ 7 cited
On Compressing U-net Using Knowledge Distillation
Karttikeya Mangalam, Mathieu Salzamann
We study the use of knowledge distillation to compress the U-net architecture. We show that, while standard distillation is not sufficient to reliably train a compressed U-net, int…