NeuroCOLT

Neural Networks and Computational Learning Theory

 

About NeuroCOLT

Papers Archive

1994 1995
1996 1997
1998 1999
2000 2001

Books

info@neurocolt.org

NeuroCOLT Technical Report NC-TR-98-021

Soft Margins for AdaBoost

Gunnar Raetsch, Takashi Onoda, & Klaus-R. Mueller
GMD

Keywords: AdaBoost, Arcing, Large Margin, Hard Margin, Soft Margin, Classification,
Support Vectors

Received: 10-AUG-98


Abstract
Recently ensemble methods like AdaBoost were successfully applied to character recognition tasks, seemingly defying the problems of overfitting. This paper shows that although AdaBoost rarely overfits in the low noise regime it clearly does so for higher noise levels. Central for under- standing this fact is the margin distribution and we find that AdaBoost achieves - doing gradient descent in an error function with respect to the margin - asymptotically a hard margin distribution, i.e. the algorithm concentrates its resources on a few hard-to-learn patterns (here an interesting overlap emerges to Support Vectors). This is clearly a sub- optimal strategy in the noisy case, and regularization, i.e. a mistrust in the data, must be introduced in the algorithm to alleviate the distortions that a dificult pattern (e.g. outliers) can cause to the margin distribution. We propose several regularization methods and generalizations of the original
AdaBoost algorithm to achieve a soft margin - a concept known from Support Vector learning. In particular we suggest (1) regularized AdaBoostReg using the soft margin directly in a modified loss function and (2) regularized linear and quadratic programming (LP/QP-) AdaBoost, where the soft margin is attained by introducing slack variables.   Extensive simulations demonstrate that the proposed regularized AdaBoost- type algorithms are useful
and competitive for noisy data.

Download Compressed Postscript