English

Neutralized Empirical Risk Minimization with Generalization Neutrality Bound

Machine Learning 2015-11-09 v1

Abstract

Currently, machine learning plays an important role in the lives and individual activities of numerous people. Accordingly, it has become necessary to design machine learning algorithms to ensure that discrimination, biased views, or unfair treatment do not result from decision making or predictions made via machine learning. In this work, we introduce a novel empirical risk minimization (ERM) framework for supervised learning, neutralized ERM (NERM) that ensures that any classifiers obtained can be guaranteed to be neutral with respect to a viewpoint hypothesis. More specifically, given a viewpoint hypothesis, NERM works to find a target hypothesis that minimizes the empirical risk while simultaneously identifying a target hypothesis that is neutral to the viewpoint hypothesis. Within the NERM framework, we derive a theoretical bound on empirical and generalization neutrality risks. Furthermore, as a realization of NERM with linear classification, we derive a max-margin algorithm, neutral support vector machine (SVM). Experimental results show that our neutral SVM shows improved classification performance in real datasets without sacrificing the neutrality guarantee.

Keywords

Cite

@article{arxiv.1511.01987,
  title  = {Neutralized Empirical Risk Minimization with Generalization Neutrality Bound},
  author = {Kazuto Fukuchi and Jun Sakuma},
  journal= {arXiv preprint arXiv:1511.01987},
  year   = {2015}
}

Comments

27 pages, 6 figures

R2 v1 2026-06-22T11:38:47.064Z