Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities

21 February 2019

Papers citing "Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities"

4 / 4 papers shown

Title
RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank Q. Garrido Randall Balestriero Laurent Najman Yann LeCun SSL 68 73 0 05 Oct 2022
Addressing Token Uniformity in Transformers via Singular Value Transformation Hanqi Yan Lin Gui Wenjie Li Yulan He 29 14 0 24 Aug 2022
Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practice Andreas Grivas Nikolay Bogoychev Adam Lopez 15 9 0 12 Mar 2022
Neural Architecture Search with Reinforcement Learning Barret Zoph Quoc V. Le 271 5,327 0 05 Nov 2016