Spectral regularization for max-margin sequence tagging

Ariadna Quattoni, Borja Balle, Xavier Carreras, Amir Globerson

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We frame max-margin learning of latent variable structured prediction models as a convex optimization problem, making use of scoring functions computed by input-output observable operator models. This learning problem can be expressed as an optimization problem involving a low-rank Hankel matrix that represents the input-output operator model. The direct outcome of our work is a new spectral regularization method for max-margin structured prediction. Our experiments confirm that our proposed regularization framework leads to an effective way of controlling the capacity of structured prediction models.

Original languageEnglish
Title of host publication31st International Conference on Machine Learning, ICML 2014
PublisherInternational Machine Learning Society (IMLS)
Pages3698-3706
Number of pages9
ISBN (Electronic)9781634393973
StatePublished - 2014
Externally publishedYes
Event31st International Conference on Machine Learning, ICML 2014 - Beijing, China
Duration: 21 Jun 201426 Jun 2014

Publication series

Name31st International Conference on Machine Learning, ICML 2014
Volume5

Conference

Conference31st International Conference on Machine Learning, ICML 2014
Country/TerritoryChina
CityBeijing
Period21/06/1426/06/14

Fingerprint

Dive into the research topics of 'Spectral regularization for max-margin sequence tagging'. Together they form a unique fingerprint.

Cite this