English

Efficient Testable Learning of General Halfspaces with Adversarial Label Noise

Machine Learning 2024-09-02 v1 Data Structures and Algorithms Machine Learning

Abstract

We study the task of testable learning of general -- not necessarily homogeneous -- halfspaces with adversarial label noise with respect to the Gaussian distribution. In the testable learning framework, the goal is to develop a tester-learner such that if the data passes the tester, then one can trust the output of the robust learner on the data.Our main result is the first polynomial time tester-learner for general halfspaces that achieves dimension-independent misclassification error. At the heart of our approach is a new methodology to reduce testable learning of general halfspaces to testable learning of nearly homogeneous halfspaces that may be of broader interest.

Keywords

Cite

@article{arxiv.2408.17165,
  title  = {Efficient Testable Learning of General Halfspaces with Adversarial Label Noise},
  author = {Ilias Diakonikolas and Daniel M. Kane and Sihan Liu and Nikos Zarifis},
  journal= {arXiv preprint arXiv:2408.17165},
  year   = {2024}
}

Comments

Presented to COLT'24

R2 v1 2026-06-28T18:28:38.353Z