video thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Fast Learning Rates for Support Vector Machines

Published on 2007-02-255118 Views

We establish learning rates to the Bayes risk for support vector machines with hinge loss (L1-SVM's). Since a theorem of Devroye states that no learning algorithm can learn with a uniform rate to the

Related categories