SDM
2007
SIAM
14 years 28 days ago
2007
SIAM
We consider the supervised learning of a binary classifier from noisy observations. We use smooth boosting to linearly combine abstaining hypotheses, each of which maps a subcube...
COLT
2001
Springer
14 years 4 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 ...