The Strength of Weak Learnability
Machine Learning
A decision-theoretic generalization of on-line learning and an application to boosting
Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Learning in Neural Networks: Theoretical Foundations
Learning in Neural Networks: Theoretical Foundations
Geometric Bounds for Generalization in Boosting
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Rademacher and Gaussian Complexities: Risk Bounds and Structural Results
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
Minimax nonparametric classification .I. Rates of convergence
IEEE Transactions on Information Theory
On the optimality of neural-network approximation using incremental algorithms
IEEE Transactions on Neural Networks
An introduction to boosting and leveraging
Advanced lectures on machine learning
Greedy algorithms for classification—consistency, convergence rates, and adaptivity
The Journal of Machine Learning Research
Generalization error bounds for Bayesian mixture algorithms
The Journal of Machine Learning Research
On the rate of convergence of regularized boosting classifiers
The Journal of Machine Learning Research
Boosting with Noisy Data: Some Views from Statistical Theory
Neural Computation
Hi-index | 0.00 |
We consider a class of algorithms for classification, which are based on sequential greedy minimization of a convex upper bound on the 0 - 1 loss function. A large class of recently popular algorithms falls within the scope of this approach, including many variants of Boosting algorithms. The basic question addressed in this paper relates to the statistical consistency of such approaches. We provide precise conditions which guarantee that sequential greedy procedures are consistent, and establish rates of convergence under the assumption that the Bayes decision boundary belongs to a certain class of smooth functions. The results are established using a form of regularization which constrains the search space at each iteration of the algorithm. In addition to providing general consistency results, we provide rates of convergence for smooth decision boundaries. A particularly interesting conclusion of our work is that Logistic function based Boosting provides faster rates of convergence than Boosting based on the exponential function used in AdaBoost.