ICML 2022spotlight5 citations

Multiclass learning with margin: exponential rates with no bias-variance trade-off

Stefano Vigogna, Giacomo Meanti, Ernesto De Vito, Lorenzo Rosasco

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.

BibTeX
@InProceedings{pmlr-v162-vigogna22a,
  title = 	 {Multiclass learning with margin: exponential rates with no bias-variance trade-off},
  author =       {Vigogna, Stefano and Meanti, Giacomo and De Vito, Ernesto and Rosasco, Lorenzo},
  booktitle = 	 {Proceedings of the 39th International Conference on Machine Learning},
  pages = 	 {22260--22269},
  year = 	 {2022},
  editor = 	 {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
  volume = 	 {162},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {17--23 Jul},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v162/vigogna22a/vigogna22a.pdf},
  url = 	 {https://proceedings.mlr.press/v162/vigogna22a.html},
  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.}
}