Convergence and Consistency of Regularized Boosting Algorithms with Stationary B-Mixing Observations.
Aurelie C. LozanoSanjeev R. KulkarniRobert E. SchapirePublished in: NIPS (2005)
Keyphrases
- boosting algorithms
- bregman divergences
- loss function
- multi class
- cost sensitive
- weak learners
- non stationary
- soft margin
- risk minimization
- weak classifiers
- generalization error
- binary classification
- base classifiers
- ensemble methods
- machine learning
- linear classifiers
- learning algorithm
- ensemble learning
- sample size
- benchmark datasets
- image classification
- learning process
- viewpoint