Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Latest commit

 

History

History

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 

Extreme Classification

  1. Extreme Classification via Adversarial Softmax Approximation [ICLR 2020] Robert Bamler, Stephan Mandt.
    • adversarial negative sample in extreme classification.
    • auxiliary task to make negative sample is uniform by decision tree.
    • proof the negative sample loss = constant + original loss.
    • proof the best signal-to-nosie in the gradient is obtained is auxiliary model is best.