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.
Vigogna, S., Meanti, G., De Vito, E., Rosasco, L. (2022). Multiclass Learning with Margin: Exponential Rates with No Bias-Variance Trade-Off. In Proceedings of Machine Learning Research (pp.22260-22269). ML Research Press.
Multiclass Learning with Margin: Exponential Rates with No Bias-Variance Trade-Off
Vigogna S.;
2022-01-01
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.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
