---
title: "Distribution-Aware Online Classifiers"
authors:
  - "Tam T. Nguyen"
  - "Kuiyu Chang"
  - "Siu Cheung Hui"
doi: "10.5591/978-1-57735-516-8/IJCAI11-241"
url: "https://ijcai.org/proceedings/2011/241"
pdf: "https://ijcai.org/proceedings/2011/0241.pdf"
venue: "Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence"
year: 2011
pages: "1427-1431"
track: ""
keywords:
---

# Distribution-Aware Online Classifiers

Tam T. Nguyen, Kuiyu Chang, Siu Cheung Hui

*Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence*, pages 1427-1431. DOI: [10.5591/978-1-57735-516-8/IJCAI11-241](https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-241)

## Abstract

We propose a family of Passive-Aggressive Mahalanobis (PAM) algorithms, which are incremental (online) binary classifiers that consider the distribution of data. PAM is in fact a generalization of the Passive-Aggressive (PA) algorithms to handle data distributions that can be represented by a covariance matrix. The update equations for PAM are derived and theoretical error loss bounds computed. We benchmarked PAM against the original PA-I, PA-II, and Confidence Weighted (CW) learning. Although PAM somewhat resembles CW in its update equations, PA minimizes differences in the weights while CW minimizes differences in weight distributions. Results on 8 classification datasets, which include a real-life micro-blog sentiment classification task, show that PAM consistently outperformed its competitors, most notably CW. This shows that a simple approach like PAM is more practical in real-life classification tasks, compared to more elegant and sophisticated approaches like CW.