Multiclass Learning with Simplex Coding
Youssef Mroueh, Tomaso Poggio, Lorenzo Rosasco et al. · arXiv (Cornell University) · 2012
In this paper we discuss a novel framework for multiclass learning, defined by a suitable coding/decoding strategy, namely the simplex coding, that allows to generalize to multiple classes a relaxation approach commonly used in binary classification. In this framework, a relaxation error analysis can be developed avoiding constraints on the considered hypotheses class. Moreover, we show that in this setting it is possible to derive the first provably consistent regularized method with training/tuning complexity which is independent to the number of classes. Tools from convex analysis are introduced that can be used beyond the scope of this paper.
Cited by 31 works. doi:10.48550/arxiv.1209.1360 Open-access PDF
Authors
References
- Pegasos
- On the algorithmic implementation of multiclass kernel-based vector machines
- Large Margin Methods for Structured and Interdependent Output Variables
- Statistical behavior and consistency of classification methods based on convex risk minimization
- 10.1162/15324430152733133
- Multicategory Support Vector Machines
- On Early Stopping in Gradient Descent Learning
- On Learning Vector-Valued Functions
- On the Consistency of Multiclass Classification Methods
- Composite Binary Losses