Jump to ContentJump to Main Navigation
Dataset Shift in Machine Learning$
Users without a subscription are not able to see the full content.

Joaquin Quiñonero-Candela, Masashi Sugiyama, Anton Schwaighofer, and Neil D. Lawrence

Print publication date: 2008

Print ISBN-13: 9780262170055

Published to MIT Press Scholarship Online: August 2013

DOI: 10.7551/mitpress/9780262170055.001.0001

Show Summary Details
Page of

PRINTED FROM MIT PRESS SCHOLARSHIP ONLINE (www.mitpress.universitypressscholarship.com). (c) Copyright The MIT Press, 2021. All Rights Reserved. An individual user may print out a PDF of a single chapter of a monograph in MITSO for personal use.date: 10 May 2021

On the Training/Test Distributions Gap: A Data Representation Learning Framework

On the Training/Test Distributions Gap: A Data Representation Learning Framework

Chapter:
(p.73) 5 On the Training/Test Distributions Gap: A Data Representation Learning Framework
Source:
Dataset Shift in Machine Learning
Author(s):

Ben-David Shai

Publisher:
The MIT Press
DOI:10.7551/mitpress/9780262170055.003.0005

This chapter discusses some dataset shift learning problems from a formal, statistical point of view. It provides definitions for “multitask learning,” “inductive transfer,” and “domain adaptation,” and discusses the parameters along which such learning scenarios may be taxonomized. The chapter then focuses on one concrete setting of domain adaptation and demonstrates how error bounds can be derived for it. These bounds can be reliably estimated from finite samples of training data, and do not rely on any assumptions concerning similarity between the domain from which the labeled training data is sampled and the target (or test) data. However, they are relative to the performance of some optimal classifier, rather than providing any absolute performance guarantee.

Keywords:   dataset shift learning, multitask learning, inductive transfer, domain adaptation, error bounds

MIT Press Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.

Please, subscribe or login to access full text content.

If you think you should have access to this title, please contact your librarian.

To troubleshoot, please check our FAQs, and if you can't find the answer there, please contact us.