Unknown

Dataset Information

0

Multicategory angle-based large-margin classification.


ABSTRACT: Large-margin classifiers are popular methods for classification. Among existing simultaneous multicategory large-margin classifiers, a common approach is to learn k different functions for a k-class problem with a sum-to-zero constraint. Such a formulation can be inefficient. We propose a new multicategory angle-based large-margin classification framework. The proposed angle-based classifiers consider a simplex-based prediction rule without the sum-to-zero constraint, and enjoy more efficient computation. Many binary large-margin classifiers can be naturally generalized for multicategory problems through the angle-based framework. Theoretical and numerical studies demonstrate the usefulness of the angle-based methods.

SUBMITTER: Zhang C 

PROVIDER: S-EPMC4629508 | biostudies-literature | 2014 Sep

REPOSITORIES: biostudies-literature

altmetric image

Publications

Multicategory angle-based large-margin classification.

Zhang Chong C   Liu Yufeng Y  

Biometrika 20140723 3


Large-margin classifiers are popular methods for classification. Among existing simultaneous multicategory large-margin classifiers, a common approach is to learn <i>k</i> different functions for a <i>k</i>-class problem with a sum-to-zero constraint. Such a formulation can be inefficient. We propose a new multicategory angle-based large-margin classification framework. The proposed angle-based classifiers consider a simplex-based prediction rule without the sum-to-zero constraint, and enjoy mor  ...[more]

Similar Datasets

| S-EPMC5120762 | biostudies-literature
| S-EPMC7731977 | biostudies-literature
| S-EPMC7434093 | biostudies-literature
| S-EPMC7444812 | biostudies-literature
| S-EPMC3960509 | biostudies-literature
| S-EPMC4795649 | biostudies-literature
| S-EPMC3867158 | biostudies-literature
| S-EPMC6089167 | biostudies-literature
| S-EPMC10788332 | biostudies-literature
| S-EPMC7044063 | biostudies-literature