Deep Networks With Large Output Spaces

23 December 2014

Papers citing "Deep Networks With Large Output Spaces"

9 / 9 papers shown

Title
ImageNet-21K Pretraining for the Masses T. Ridnik Emanuel Ben-Baruch Asaf Noy Lihi Zelnik-Manor SSeg VLM CLIP 187 690 0 22 Apr 2021
Sampled Softmax with Random Fourier Features A. S. Rawat Jiecao Chen Felix X. Yu A. Suresh Sanjiv Kumar 39 55 0 24 Jul 2019
A no-regret generalization of hierarchical softmax to extreme multi-label classification Marek Wydmuch Kalina Jasinska Mikhail Kuznetsov R. Busa-Fekete Krzysztof Dembczyñski 29 100 0 27 Oct 2018
Beyond One-hot Encoding: lower dimensional target embedding Pau Rodríguez López Miguel Angel Bautista Jordi Gonzalez Sergio Escalera 11 335 0 28 Jun 2018
Improving Negative Sampling for Word Representation using Self-embedded Features Long Chen Fajie Yuan J. Jose Weinan Zhang SSL 29 43 0 26 Oct 2017
Exact gradient updates in time independent of output size for the spherical loss family Pascal Vincent A. D. Brébisson Xavier Bouthillier 13 2 0 26 Jun 2016
Strategies for Training Large Vocabulary Neural Language Models Welin Chen David Grangier Michael Auli VLM 24 139 0 15 Dec 2015
BlackOut: Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies Shihao Ji S.V.N. Vishwanathan N. Satish Michael J. Anderson Pradeep Dubey 44 77 0 21 Nov 2015
Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets Pascal Vincent A. D. Brébisson Xavier Bouthillier 34 49 0 22 Dec 2014