Google Research

The perils of being unhinged: On the accuracy of classifiers minimizing a noise-robust convex loss

Neural Computation (2022) (to appear)

Abstract

van Rooyen et al. introduced a notion of convex loss functions being robust to random classification noise, and established that the ``unhinged'' loss function is robust in this sense. In this note we study the accuracy of binary classifiers obtained by minimizing the unhinged loss, and observe that even for simple linearly separable data distributions, minimizing the unhinged loss may only yield a binary classifier with accuracy no better than random guessing.

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work