Mistake Bound Model | Sciweavers

36

SIGIR
2002
ACM

147views Information Technology» more SIGIR 2002»

A new family of online algorithms for category ranking

13 years 11 months ago

We describe a new family of topic-ranking algorithms for multi-labeled documents. The motivation for the algorithms stems from recent advances in online learning algorithms. The a...

Koby Crammer, Yoram Singer

claim paper

Read More »

27

click to vote

COLT
1999
Springer

96views Machine Learning» more COLT 1999»

On a Generalized Notion of Mistake Bounds

14 years 3 months ago

Download www.comp.nus.edu.sg

This paper proposes the use of constructive ordinals as mistake bounds in the on-line learning model. This approach elegantly generalizes the applicability of the on-line mistake ...

Sanjay Jain, Arun Sharma

claim paper

Read More »

29

click to vote

ICML
1997
IEEE

135views Machine Learning» more ICML 1997»

Expected Mistake Bound Model for On-Line Reinforcement Learning

15 years 7 days ago