PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

An Analysis of Generalization Error in Relevant Subtask Learning
Keisuke Yamazaki and Samuel Kaski
In: Advances in Neuro-Information Processing, 15th International Conference, ICONIP 2008 (2009) Springer , Berlin , pp. 629-637.


A recent variant of multi-task learning uses the other tasks to help in learning a task-of-interest, for which there is too little training data. The task can be classification, prediction, or density estimation. The problem is that only some of the data of the other tasks are rele- vant or representative for the task-of-interest. It has been experimentally demonstrated that a generative model works well in this relevant subtask learning task. In this paper we analyze the generalization error of the model, to show that it is smaller than in standard alternatives, and to point out connections to semi-supervised learning, multi-task learning, and active learning or covariate shift.

EPrint Type:Book Section
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:6299
Deposited By:Samuel Kaski
Deposited On:08 March 2010