A unifying approach on bias and variance analysis for classification
Machine Learning
2021-01-14 v2 Machine Learning
Abstract
Standard bias and variance (B&V) terminologies were originally defined for the regression setting and their extensions to classification have led to several different models / definitions in the literature. In this paper, we aim to provide the link between the commonly used frameworks of Tumer & Ghosh (T&G) and James. By unifying the two approaches, we relate the B&V defined for the 0/1 loss to the standard B&V of the boundary distributions given for the squared error loss. The closed form relationships provide a deeper understanding of classification performance, and their use is demonstrated in two case studies.
Cite
@article{arxiv.2101.01765,
title = {A unifying approach on bias and variance analysis for classification},
author = {Cemre Zor and Terry Windeatt},
journal= {arXiv preprint arXiv:2101.01765},
year = {2021}
}
Comments
17 pages, 3 figures