Are there training-set bounds for arbitrary losses, such as F1, MAP, AUC, etc? And test-set bounds?

asked Sep 27 '10 at 07:41

Alexandre%20Passos's gravatar image

Alexandre Passos ♦
2554154278421

edited Dec 03 '10 at 07:16


One Answer:

This Reid and Williamson paper, Information, Divergence and Risk for Binary Experiments somewhat answers this question.

answered Nov 02 '10 at 15:36

Alexandre%20Passos's gravatar image

Alexandre Passos ♦
2554154278421

Your answer
toggle preview

powered by OSQA

User submitted content is under Creative Commons: Attribution - Share Alike; Other things copyright (C) 2010, MetaOptimize LLC.