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

12/08/2021
by   Philip M. Long, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/27/2012

Minimizing The Misclassification Error Rate Using a Surrogate Convex Loss

We carefully study how well minimizing convex surrogate loss functions, ...
research
11/18/2019

Attribute noise robust binary classification

We consider the problem of learning linear classifiers when both feature...
research
01/08/2019

Cost Sensitive Learning in the Presence of Symmetric Label Noise

In binary classification framework, we are interested in making cost sen...
research
11/05/2019

An Alternative Probabilistic Interpretation of the Huber Loss

The Huber loss is a robust loss function used for a wide range of regres...
research
02/10/2020

Stability for the Training of Deep Neural Networks and Other Classifiers

We examine the stability of loss-minimizing training processes that are ...
research
07/07/2021

RISAN: Robust Instance Specific Abstention Network

In this paper, we propose deep architectures for learning instance speci...
research
06/15/2018

On the exact minimization of saturated loss functions for robust regression and subspace estimation

This paper deals with robust regression and subspace estimation and more...

Please sign up or login with your details

Forgot password? Click here to reset