141 search results - page 8 / 29 » Learning r-of-k Functions by Boosting |
EUROCOLT
1995
Springer
15 years 3 months ago
1995
Springer
k. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multi...
COLT
2008
Springer
15 years 1 months ago
2008
Springer
Boosting algorithms build highly accurate prediction mechanisms from a collection of lowaccuracy predictors. To do so, they employ the notion of weak-learnability. The starting po...
ICML
2008
IEEE
16 years 17 days ago
2008
IEEE
A broad class of boosting algorithms can be interpreted as performing coordinate-wise gradient descent to minimize some potential function of the margins of a data set. This class...
111
click to vote
ICML
2007
IEEE
16 years 17 days ago
2007
IEEE
We study the problem of learning a classification task in which only a dissimilarity function of the objects is accessible. That is, data are not represented by feature vectors bu...
ICML
2004
IEEE
16 years 17 days ago
2004
IEEE
Surrogate maximization (or minimization) (SM) algorithms are a family of algorithms that can be regarded as a generalization of expectation-maximization (EM) algorithms. There are...