19 search results - page 3 / 4 » colt 2001 |
119
click to vote
COLT
2001
Springer
15 years 2 months ago
2001
Springer
We prove strong noise-tolerance properties of a potential-based boosting algorithm, similar to MadaBoost (Domingo and Watanabe, 2000) and SmoothBoost (Servedio, 2003). Our analysi...
COLT
2001
Springer
15 years 2 months ago
2001
Springer
We describe a new boosting algorithm which generates only smooth distributions which do not assign too much weight to any single example. We show that this new boosting algorithm ...
72
Voted
COLT
2001
Springer
15 years 2 months ago
2001
Springer
A classical learning problem in Inductive Inference consists of identifying each function of a given class of recursive functions from a finite number of its output values. Unifor...
COLT
2001
Springer
15 years 2 months ago
2001
Springer
In this paper, we examine on-line learning problems in which the target concept is allowed to change over time. In each trial a master algorithm receives predictions from a large ...
COLT
2001
Springer
15 years 2 months ago
2001
Springer
We consider geometric conditions on a labeled data set which guarantee that boosting algorithms work well when linear classifiers are used as weak learners. We start by providing ...