Algorithmic stability and hypothesis complexity

Liu, T; Lugosi, G; Neu, G; Tao, D

Algorithmic stability and hypothesis complexity

Liu, T Lugosi, G Neu, G Tao, D

Permalink

Publication Type:: Conference Proceeding
Citation:: 34th International Conference on Machine Learning, ICML 2017, 2017, 5 pp. 3413 - 3421
Issue Date:: 2017-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (236.33 kB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Liu, T	en_US
dc.contributor.author	Lugosi, G	en_US
dc.contributor.author	Neu, G	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.date.issued	2017-01-01	en_US
dc.identifier.citation	34th International Conference on Machine Learning, ICML 2017, 2017, 5 pp. 3413 - 3421	en_US
dc.identifier.isbn	9781510855144	en_US
dc.identifier.uri	http://hdl.handle.net/10453/127219
dc.description.abstract	© 2017 by the author(s). We introduce a notion of algorithmic stability of learning algorithms-that we term argument stability-that captures stability of the hypothesis output by the learning algorithm in the normed space of functions from which hypotheses are selected. The main result of the paper bounds the generalization error of any learning algorithm in terms of its argument stability. The bounds are based on martingale inequalities in the Banach space to which the hypotheses belong. We apply the general bounds to bound the performance of some learning algorithms based on empirical risk minimization and stochastic gradient descent.	en_US
dc.relation.ispartof	34th International Conference on Machine Learning, ICML 2017	en_US
dc.title	Algorithmic stability and hypothesis complexity	en_US
dc.type	Conference Proceeding
utslib.citation.volume	5	en_US
utslib.for	0803 Computer Software	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	open_access
pubs.publication-status	Published	en_US
pubs.volume	5	en_US

Abstract:

© 2017 by the author(s). We introduce a notion of algorithmic stability of learning algorithms-that we term argument stability-that captures stability of the hypothesis output by the learning algorithm in the normed space of functions from which hypotheses are selected. The main result of the paper bounds the generalization error of any learning algorithm in terms of its argument stability. The bounds are based on martingale inequalities in the Banach space to which the hypotheses belong. We apply the general bounds to bound the performance of some learning algorithms based on empirical risk minimization and stochastic gradient descent.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/127219