Tight Risk Bounds for Multi-Class Margin Classifiers
This work provides a theoretical foundation for multi-class classification, which is incremental as it builds on existing risk bound methods.
The authors tackled the problem of risk estimation for large-margin multi-class classifiers by proposing a novel risk bound that incorporates the marginal distribution and Rademacher complexity, proving it is tight in the number of classes.
We consider a problem of risk estimation for large-margin multi-class classifiers. We propose a novel risk bound for the multi-class classification problem. The bound involves the marginal distribution of the classifier and the Rademacher complexity of the hypothesis class. We prove that our bound is tight in the number of classes. Finally, we compare our bound with the related ones and provide a simplified version of the bound for the multi-class classification with kernel based hypotheses.