en-de
en-es
en-fr
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
Random Classification Noise Defeats All Convex Potential Boosters
Published on 2008-08-063590 Views
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 includes AdaBoost, L