PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Complexity versus Agreement for Many Views
Odalric-Ambrym Maillard and Nicolas Vayatis
In: Algorithmic Learning Theory, 20th International Conference Lecture Notes in Computer Science , 20 (5809). (2009) Springer , Porto, Portugal , pp. 232-246. ISBN 978-3-642-04413-7


The paper considers the problem of semi-supervised multi-view classification, where each view corresponds to a Reproducing Kernel Hilbert Space. An algorithm based on co-regularization methods with extra penalty terms reflecting smoothness and general agreement properties is proposed. We first provide explicit tight control on the Rademacher (L 1) complexity of the corresponding class of learners for arbitrary many views, then give the asymptotic behavior of the bounds when the co-regularization term increases, making explicit the relation between consistency of the views and reduction of the search space. Since many views involve many parameters, we third provide a parameter selection procedure, based on the stability approach with clustering and localization arguments. To this aim, we give an explicit bound on the variance (L 2-diameter) of the class of functions. Finally we illustrate the algorithm through simulations on toy examples.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Book Section
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:5994
Deposited By:Odalric-Ambrym Maillard
Deposited On:08 March 2010