Multiclass Learning with Simplex Coding

Abstract

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.

References in corpus (2)

• Composite Binary Losses
• Multicategory vertex discriminant analysis for high-dimensional data

Cited by in corpus (8)

• Multiclass Classification Calibration Functions
• Structured Prediction for Conditional Meta-Learning
• Random Fourier Features for Operator-Valued Kernels
• Convex variational methods for multiclass data segmentation on graphs
• A Unifying Framework in Vector-valued Reproducing Kernel Hilbert Spaces for Manifold Regularization and Co-Regularized Multi-view Learning
• Bounds for Vector-Valued Function Estimation
• LightMC: A Dynamic and Efficient Multiclass Decomposition Algorithm
• From Kernel Machines to Ensemble Learning