Poster
Learning with Symmetric Label Noise: The Importance of Being Unhinged
Brendan van Rooyen · Aditya Menon · Robert Williamson

Thu Dec 10th 11:00 AM -- 03:00 PM @ 210 C #72 #None

Convex potential minimisation is the de facto approach to binary classification. However, Long and Servedio [2008] proved that under symmetric label noise (SLN), minimisation of any convex potential over a linear function class can result in classification performance equivalent to random guessing. This ostensibly shows that convex losses are not SLN-robust. In this paper, we propose a convex, classification-calibrated loss and prove that it is SLN-robust. The loss avoids the Long and Servedio [2008] result by virtue of being negatively unbounded. The loss is a modification of the hinge loss, where one does not clamp at zero; hence, we call it the unhinged loss. We show that the optimal unhinged solution is equivalent to that of a strongly regularised SVM, and is the limiting solution for any convex potential; this implies that strong l2 regularisation makes most standard learners SLN-robust. Experiments confirm the unhinged loss’ SLN-robustness.

Author Information

Brendan van Rooyen (NICTA)
Aditya Menon (NICTA)
Robert Williamson (NICTA)

More from the Same Authors