Minimizing The Misclassification Error Rate Using a Surrogate Convex Loss

06/27/2012
by   Shai Ben-David, et al.
0

We carefully study how well minimizing convex surrogate loss functions, corresponds to minimizing the misclassification error rate for the problem of binary classification with linear predictors. In particular, we show that amongst all convex surrogate losses, the hinge loss gives essentially the best possible bound, of all convex loss functions, for the misclassification error rate of the resulting linear predictor in terms of the best possible margin error rate. We also provide lower bounds for specific convex surrogates that show how different commonly used losses qualitatively differ from each other.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

12/28/2016

The Pessimistic Limits of Margin-based Losses in Semi-supervised Learning

We show that for linear classifiers defined by convex margin-based surro...
12/08/2021

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

van Rooyen et al. introduced a notion of convex loss functions being rob...
10/16/2018

Stochastic Negative Mining for Learning with Large Output Spaces

We consider the problem of retrieving the most relevant labels for a giv...
01/05/2021

A Symmetric Loss Perspective of Reliable Machine Learning

When minimizing the empirical risk in binary classification, it is a com...
07/17/2019

An Embedding Framework for Consistent Polyhedral Surrogates

We formalize and study the natural approach of designing convex surrogat...
04/09/2015

`local' vs. `global' parameters -- breaking the gaussian complexity barrier

We show that if F is a convex class of functions that is L-subgaussian, ...
01/27/2019

On Symmetric Losses for Learning from Corrupted Labels

This paper aims to provide a better understanding of a symmetric loss. F...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.