Adaptive Sampled Softmax with Kernel Based Sampling

Guy Blanc
Guy Blanc

international conference on machine learning, 2018.

Cited by: 14|Bibtex|Views89
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Softmax is the most commonly used output function for multiclass problems and is widely used in areas such as vision, natural language processing, and recommendation. A softmax model has linear costs in the number of classes which makes it too expensive for many real-world problems. A common approach to speed up training involves sampling...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments