Multiclass learning with margin: exponential rates with no bias-variance trade-off
This work addresses multiclass classification theory, generalizing binary results to multiclass, which is incremental but important for machine learning practitioners.
The paper tackles the problem of multiclass classification error bounds under margin conditions, proving that classification error decreases exponentially fast without a bias-variance trade-off for various methods, with rates depending on margin assumptions.
We study the behavior of error bounds for multiclass classification under suitable margin conditions. For a wide variety of methods we prove that the classification error under a hard-margin condition decreases exponentially fast without any bias-variance trade-off. Different convergence rates can be obtained in correspondence of different margin assumptions. With a self-contained and instructive analysis we are able to generalize known results from the binary to the multiclass setting.