Ensemble Learning using Error Correcting Output Codes: New Classification Error Bounds

TL;DR

This paper introduces new theoretical bounds on the error rates of ECOC classifiers, demonstrating exponential decay with codeword length and validating the approach through experiments on multiple datasets.

Contribution

It provides the first error bounds for ECOC classifiers considering both independent and correlated base classifiers, with experimental validation.

Findings

Error bounds decay exponentially with codeword length.

Correlation among classifiers affects classification accuracy.

Experimental results support theoretical bounds.

Abstract

New bounds on classification error rates for the error-correcting output code (ECOC) approach in machine learning are presented. These bounds have exponential decay complexity with respect to codeword length and theoretically validate the effectiveness of the ECOC approach. Bounds are derived for two different models: the first under the assumption that all base classifiers are independent and the second under the assumption that all base classifiers are mutually correlated up to first-order. Moreover, we perform ECOC classification on six datasets and compare their error rates with our bounds to experimentally validate our work and show the effect of correlation on classification accuracy.