On the Consistency of Output Code Based Learning Algorithms for Multiclass Learning Problems.
Harish G. RamaswamyBalaji Srinivasan BabuShivani AgarwalRobert C. WilliamsonPublished in: COLT (2014)
Keyphrases
- learning problems
- multi class
- binary classification
- learning algorithm
- multiclass learning
- error correcting output codes
- multiclass classification
- learning tasks
- machine learning algorithms
- kernel methods
- machine learning
- multiclass problems
- supervised learning
- binary classifiers
- support vector machine
- semi supervised learning
- statistical learning theory
- binary classification problems
- multiple kernel learning
- reinforcement learning
- feature selection
- multi task
- pairwise
- sample complexity
- multi task learning
- pac learning
- perceptron algorithm
- learning models
- cost sensitive
- boosting algorithms
- generalization bounds
- feature space
- feature extraction
- kernel function
- dimensionality reduction
- training data