Abstract
One basic property of the boosting algorithm is its ability to reduce the training error, subject to the critical assumption that the base learners generate ‘weak’ (or more appropriately, ‘weakly accurate’) hypotheses that are better that random guessing. We exploit analogies between regression and classification to give a characterization on what base learners generate weak hypotheses, by introducing a geometric concept called the angular span for the base hypothesis space. The exponential convergence rates of boosting algorithms are shown to be bounded below by essentially the angular spans. Sufficient conditions for nonzero angular span are also given and validated for a wide class of regression and classification systems.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Breiman, L. (1998). Arcing classifiers. The Annals of Statistics, 26 801–849.
Breiman, L. (1997). Prediction games and arcing classifiers. Technical Report 504, Statistics Department, University of California at Berkeley, 1997.
Breiman, L. (1997). Arcing the edge. Technical Report 486, Statistics Department, University of California at Berkeley, 1997
Freund, Y. (1995). Boosting a weak learning algorithm by majority. Information and Computation, 121 256–285.
Freund, Y. and Schapire, R. E. (1996). Game theory, on-line prediction and boosting. Proceedings of the Ninth Annual Conference on Computational Learning Theory, 325–332.
Freund, Y. and Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55 119–139.
Friedman, J. H. (1999). Greedy function approximation: a gradient boosting machine. Technical Report, Department of Statistics, Stanford University
Friedman, J., Hastie, T. Tibshirani, R. (1999). Additive logistic regression: a statistical view of boosting. Technical Report, Department of Statistics, Stanford University
Goldmann, M., Hastad, J., and Razborov, A. (1992). Majority gates vs. general weighted threshold gates. Computational Complexity, 2 277–300.
Jacobs, R. A., Jordan, M. I., Nowlan, S. J., Hinton, G. E. (1991). Adaptive mixtures of local experts. Neural Comp3 79–87.
Jiang, W. (1999). Large time behavior of boosting algorithms for regression and classification. Technical Report, Department of Statistics, Northwestern University.
Jiang, W. (2000). On weak base learners for boosting regression and classification. Technical Report, Department of Statistics, Northwestern University.
Mason, L., Baxter, J., Bartlett, P. Frean, M. Boosting algorithms as gradient descent in function space. Technical Report, Department of Systems Engineering, Australian National University
Schapire, R. E. (1990). The strength of weak learnability. Machine Learning, 5 197–227.
Schapire, R. E. (1999). Theoretical views of boosting. Computational Learning Theory: Fourth European Conference, EuroCOLT’99, 1–10.
Schapire, R. E., Freund, Y., Bartlett, P. AND Lee, W. S. (1998). Boosting the margin: A new explanation for the effectiveness of voting methods. The Annals of Statistics, 26 1651–1686.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jiang, W. (2000). Some Results on Weakly Accurate Base Learners for Boosting Regression and Classification. In: Multiple Classifier Systems. MCS 2000. Lecture Notes in Computer Science, vol 1857. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45014-9_8
Download citation
DOI: https://doi.org/10.1007/3-540-45014-9_8
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67704-8
Online ISBN: 978-3-540-45014-6
eBook Packages: Springer Book Archive