eprintid: 1769
rev_number: 6
eprint_status: archive
userid: 46
dir: disk0/00/00/17/69
datestamp: 2013-09-17 12:55:31
lastmod: 2015-02-18 12:01:09
status_changed: 2013-09-17 12:55:31
type: book_section
succeeds: 1700
metadata_visibility: show
creators_name: Gnecco, Giorgio
creators_name: Gori, Marco
creators_name: Melacci, Stefano
creators_name: Sanguineti, Marcello
creators_id: giorgio.gnecco@imtlucca.it
creators_id: 
creators_id: 
creators_id: 
title: Learning with Hard Constraints
ispublished: pub
subjects: QA75
divisions: CSA
full_text_status: none
pres_type: paper
keywords: Learning from constraints; learning with prior knowledge; multi-task learning; support constraints; constrained variational calculus
note: 23rd International Conference on Artificial Neural Networks Sofia, Bulgaria, September 10-13, 2013. Proceedings
abstract: A learning paradigm is proposed, in which one has both classical supervised examples and constraints that cannot be violated, called here “hard constraints”, such as those enforcing the probabilistic normalization of a density function or imposing coherent decisions of the classifiers acting on different views of the same pattern. In contrast, supervised examples can be violated at the cost of some penalization (quantified by the choice of a suitable loss function) and so play the roles of “soft constraints”. Constrained variational calculus is exploited to derive a representation theorem which provides a description of the “optimal body of the agent”, i.e. the functional structure of the solution to the proposed learning problem. It is shown that the solution can be represented in terms of a set of “support constraints”, thus extending the well-known notion of “support vectors”.
date: 2013
series: Lecture notes in computer science
number: 8131
publisher: Springer
pagerange: 146-153
event_title: 23rd International Conference on Artificial Neural Networks
event_location: Sofia, Bulgaria
event_dates: September 10th-13th, 2013
event_type: conference
id_number: 10.1007/978-3-642-40728-4_19
refereed: TRUE
isbn: 978-3-642-40728-4
book_title: Artificial Neural Networks and Machine Learning – ICANN 2013
official_url: http://dx.doi.org/10.1007/978-3-642-40728-4_19
related_url_type: org
citation:   Gnecco, Giorgio and Gori, Marco and Melacci, Stefano and Sanguineti, Marcello  Learning with Hard Constraints.   In:  Artificial Neural Networks and Machine Learning – ICANN 2013.   Lecture notes in computer science  (8131).  Springer, pp. 146-153.  ISBN 978-3-642-40728-4      (2013)