29 search results - page 2 / 6 » Learning parities in the mistake-bound model |
COLT
1999
Springer
15 years 1 months ago
1999
Springer
We consider the problem of learning to predict as well as the best in a group of experts making continuous predictions. We assume the learning algorithm has prior knowledge of the ...
ALT
2008
Springer
15 years 6 months ago
2008
Springer
We consider the problem of learning to predict as well as the best in a group of experts making continuous predictions. We assume the learning algorithm has prior knowledge of the ...
SIGIR
2002
ACM
14 years 9 months ago
2002
ACM
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...
ICML
2010
IEEE
14 years 10 months ago
2010
IEEE
This paper develops a generalized apprenticeship learning protocol for reinforcementlearning agents with access to a teacher who provides policy traces (transition and reward obse...
ICML
2003
IEEE
15 years 10 months ago
2003
IEEE
We present a new type of multi-class learning algorithm called a linear-max algorithm. Linearmax algorithms learn with a special type of attribute called a sub-expert. A sub-exper...