Optimal Learning of Kernel Logistic Regression for Complex Classification Scenarios
Hongwei Wen, Annika Betken, Hanyuan Hang
Abstract
Complex classification scenarios, including long-tailed learning, domain adaptation, and transfer learning, present substantial challenges for traditional algorithms. Conditional class probability (CCP) predictions have recently become critical components of many state-of-the-art algorithms designed to address these challenging scenarios. Among kernel methods, kernel logistic regression (KLR) is distinguished by its effectiveness in predicting CCPs through the minimization of the cross-entropy (CE) loss. Despite the empirical success of CCP-based approaches, the theoretical understanding of their performance, particularly regarding the CE loss, remains limited. In this paper, we bridge this gap by demonstrating that KLR-based algorithms achieve minimax optimal convergence rates for the CE loss under mild assumptions in these complex tasks, thereby establishing their theoretical efficiency in such demanding contexts.
BibTeX
@inproceedings{
wen2025optimal,
title={Optimal Learning of Kernel Logistic Regression for Complex Classification Scenarios},
author={Hongwei Wen and Annika Betken and Hanyuan Hang},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=WlhVRh2rQ0}
}