Multiclass learning with margin: exponential rates with no bias-variance trade-off
Machine Learning
2022-02-04 v1 Machine Learning
Abstract
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.
Cite
@article{arxiv.2202.01773,
title = {Multiclass learning with margin: exponential rates with no bias-variance trade-off},
author = {Stefano Vigogna and Giacomo Meanti and Ernesto De Vito and Lorenzo Rosasco},
journal= {arXiv preprint arXiv:2202.01773},
year = {2022}
}