tlooto
Sign up
Adversarial Robustness in Machine LearningImbalanced Data Classification TechniquesMachine Learning and Algorithms

An Arbitrarily Tight Lower Bound for the Bhattacharyya Upper Bound on Bayes Error

Hossein Kazemzadeh Gharechopogh, Adel Mohammadpour

2026.2.11JOURNAL OF CLASSIFICATION

DOI: 10.1007/s00357-026-09537-6

Abstract

This study introduces a novel upper bound for the Bayes error that is a lower bound for the traditional Bhattacharyya bound for binary classifiers. We demonstrate its superior tightness through analytical comparisons and empirical evaluations against known bounds.

Citation format

GHARECHOPOGH, Hossein Kazemzadeh; MOHAMMADPOUR, Adel. An arbitrarily tight lower bound for the bhattacharyya upper bound on bayes error. JOURNAL OF CLASSIFICATION, 2026, 43(2): 334–351.