Learning from Multiple Sources

Loading...
Thumbnail Image
Penn collection
Departmental Papers (CIS)
Degree type
Discipline
Subject
error bounds
multi-task learning
Funder
Grant number
License
Copyright date
Distributor
Related resources
Contributor
Abstract

We consider the problem of learning accurate models from multiple sources of "nearby" data. Given distinct samples from multiple data sources and estimates of the dissimilarities between these sources, we provide a general theory of which samples should be used to learn models for each source. This theory is applicable in a broad decision-theoretic learning framework, and yields general results for classification and regression. A key component of our approach is the development of approximate triangle inequalities for expected loss, which may be of independent interest. We discuss the related problem of learning parameters of a distribution from multiple data sources. Finally, we illustrate our theory through a series of synthetic simulations.

Advisor
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Publication date
2008-06-01
Journal title
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Copyright 2008 MIT Press. Crammer, K., Kearns, M., and Wortman, J. 2008. Learning from Multiple Sources. J. Mach. Learn. Res. 9 (Jun. 2008), 1757-1774. Publisher URL: http://jmlr.csail.mit.edu/papers/v9/crammer08a.html
Recommended citation
Collection