Learning theoretical bounds for quantities other than accuracy

2	Are there training-set bounds for arbitrary losses, such as F1, MAP, AUC, etc? And test-set bounds? loss-function references bounds learning-theory asked Sep 27 '10 at 07:41 Alexandre Passos ♦ 18937●44●214●333 edited Dec 03 '10 at 07:16

One Answer:

oldest newest most voted

0	This Reid and Williamson paper, Information, Divergence and Risk for Binary Experiments somewhat answers this question. answered Nov 02 '10 at 15:36 Alexandre Passos ♦ 18937●44●214●333

Your answer

toggle preview

community wiki

Once you sign in you will be able to subscribe for any updates here

Tags:

Asked: Sep 27 '10 at 07:41

Seen: 739 times

Last updated: Dec 03 '10 at 07:16