Sigsoftmax: Reanalysis of the Softmax Bottleneck

28 May 2018

Papers citing "Sigsoftmax: Reanalysis of the Softmax Bottleneck"

6 / 6 papers shown

Title
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
Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models Phil Chen Masha Itkina Ransalu Senanayake Mykel J. Kochenderfer 41 6 0 27 Oct 2021
Softmax-based Classification is k-means Clustering: Formal Proof, Consequences for Adversarial Attacks, and Improvement through Centroid Based Tailoring Sibylle Hess W. Duivesteijn Decebal Constantin Mocanu 25 12 0 07 Jan 2020
Improving Neural Language Modeling via Adversarial Training Dilin Wang Chengyue Gong Qiang Liu AAML 43 115 0 10 Jun 2019
Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities O. Ganea Sylvain Gelly Gary Bécigneul Aliaksei Severyn 29 18 0 21 Feb 2019
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context Zihang Dai Zhilin Yang Yiming Yang J. Carbonell Quoc V. Le Ruslan Salakhutdinov VLM 38 3,679 0 09 Jan 2019