← Back to papers
2022 ICML ICML 2022

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

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.

🐝 Cross-Pollinator — Artificial Intelligence, Computer Vision, Deep Learning, Machine Learning, Mathematics & Optimization, Reinforcement Learning, Speech & Audio
🧭 Keyword Pioneer — hard-margin condition
🐣 Hot Topic Early Bird — multiclass classification

Authors

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

Topics

Machine Learning > Core Methods > Classification Machine Learning > Optimization & Theory > Learning Theory Machine Learning > Optimization & Theory > Statistical Learning Machine Learning > Learning Types > Classification

Keywords

multiclass classification margin theory margin condition exponential convergence error bound bias-variance trade-off hard-margin condition
Download PDF

Related papers

A Tree-based Model Averaging Approach for Personalized Treatment Effect Estimation from Heterogeneous Data Sources 2022
Generic Coreset for Scalable Learning of Monotonic Kernels: Logistic Regression, Sigmoid and more 2022
Active fairness auditing 2022
Toward Compositional Generalization in Object-Oriented World Modeling 2022
Robustness Verification for Contrastive Learning 2022