Complexity versus Agreement for Many Views

Odalric-Ambrym Maillard, Nicolas Vayatis.
In ALT 2009, pages 232–246, 2009.

[Download]

Abstract:

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 (L1 ) 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. Third we provide an illustration through simulations on toy examples. With many views, a parameter selection procedure is based on the stability approach with clustering and localization arguments. The last new result is an explicit bound on the L2 -diameter of the class of functions.

You can dowload the paper from the ALT website (here) or from the HAL online open depository* (here).

Bibtex:

@inproceedings{MaillardV09, author = {{Odalric-Ambrym} Maillard and Nicolas Vayatis}, title = {Complexity versus Agreement for Many Views.}, booktitle = {Algorithmic Learning Theory, 20th International Conference, {ALT} 2009, Porto, Portugal, October 3-5, 2009.}, year = {2009}, pages = {232–246}, editor = {Ricard Gavald\`{a} and G\`{a}bor Lugosi and Thomas Zeugmann and Sandra Zilles}, series = {Lecture Notes in Computer Science}, year = {2009}, volume = {5809}, publisher = {Springer} }