Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities

Octavian Ganea, Sylvain Gelly, Gary Bécigneul, Aliaksei Severyn. Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities. In Kamalika Chaudhuri, Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA. Volume 97 of Proceedings of Machine Learning Research, pages 2073-2082, PMLR, 2019. [doi]

Abstract

Abstract is missing.