Binary Classification with a Pseudo Exponential Model and Its Application for Multi-Task Learning †

Entropy

Takashi Takenouchi³  Osamu Komori¹  Shinto Eguchi¹  Frຝéric Barbaresco² 

[1] The Institute of Statistical Mathematics, 10-3 Midori-cho, Tachikawa, Tokyo 190-8562, Japan; E-Mails:;id="af1-entropy-17-05673">1Future University Hakodate, 116-2 Kamedanakano, Hakodate Hokkaido 041-8655, Jap;Future University Hakodate, 116-2 Kamedanakano, Hakodate Hokkaido 041-8655, Japan

关键词: multi-task learning;    Itakura–Saito distance;    pseudo model;    un-normalized model;   

DOI  :  10.3390/e17085673

来源: mdpi

【 摘 要 】

In this paper, we investigate the basic properties of binary classification with a pseudo model based on the Itakura–Saito distance and reveal that the Itakura–Saito distance is a unique appropriate measure for estimation with the pseudo model in the framework of general Bregman divergence. Furthermore, we propose a novel multi-task learning algorithm based on the pseudo model in the framework of the ensemble learning method. We focus on a specific setting of the multi-task learning for binary classification problems. The set of features is assumed to be common among all tasks, which are our targets of performance improvement. We consider a situation where the shared structures among the dataset are represented by divergence between underlying distributions associated with multiple tasks. We discuss statistical properties of the proposed method and investigate the validity of the proposed method with numerical experiments.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.