Localized Multiple Kernel Learning—A Convex Approach

Yunwen Lei, Alexander Binder, Urun Dogan, Marius Kloft
Proceedings of The 8th Asian Conference on Machine Learning, PMLR 63:81-96, 2016.

Abstract

We propose a localized approach to multiple kernel learning that can be formulated as a convex optimization problem over a given cluster structure. For which we obtain generalization error guarantees and derive an optimization algorithm based on the Fenchel dual representation. Experiments on real-world datasets from the application domains of computational biology and computer vision show that convex localized multiple kernel learning can achieve higher prediction accuracies than its global and non-convex local counterparts.

Cite this Paper

BibTeX
@InProceedings{pmlr-v63-lei63, title = {Localized Multiple Kernel Learning---A Convex Approach}, author = {Lei, Yunwen and Binder, Alexander and Dogan, Urun and Kloft, Marius}, booktitle = {Proceedings of The 8th Asian Conference on Machine Learning}, pages = {81--96}, year = {2016}, editor = {Durrant, Robert J. and Kim, Kee-Eung}, volume = {63}, series = {Proceedings of Machine Learning Research}, address = {The University of Waikato, Hamilton, New Zealand}, month = {16--18 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v63/lei63.pdf}, url = {https://proceedings.mlr.press/v63/lei63.html}, abstract = {We propose a localized approach to multiple kernel learning that can be formulated as a convex optimization problem over a given cluster structure. For which we obtain generalization error guarantees and derive an optimization algorithm based on the Fenchel dual representation. Experiments on real-world datasets from the application domains of computational biology and computer vision show that convex localized multiple kernel learning can achieve higher prediction accuracies than its global and non-convex local counterparts.} }
Endnote
%0 Conference Paper %T Localized Multiple Kernel Learning—A Convex Approach %A Yunwen Lei %A Alexander Binder %A Urun Dogan %A Marius Kloft %B Proceedings of The 8th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Robert J. Durrant %E Kee-Eung Kim %F pmlr-v63-lei63 %I PMLR %P 81--96 %U https://proceedings.mlr.press/v63/lei63.html %V 63 %X We propose a localized approach to multiple kernel learning that can be formulated as a convex optimization problem over a given cluster structure. For which we obtain generalization error guarantees and derive an optimization algorithm based on the Fenchel dual representation. Experiments on real-world datasets from the application domains of computational biology and computer vision show that convex localized multiple kernel learning can achieve higher prediction accuracies than its global and non-convex local counterparts.
RIS
TY - CPAPER TI - Localized Multiple Kernel Learning—A Convex Approach AU - Yunwen Lei AU - Alexander Binder AU - Urun Dogan AU - Marius Kloft BT - Proceedings of The 8th Asian Conference on Machine Learning DA - 2016/11/20 ED - Robert J. Durrant ED - Kee-Eung Kim ID - pmlr-v63-lei63 PB - PMLR DP - Proceedings of Machine Learning Research VL - 63 SP - 81 EP - 96 L1 - http://proceedings.mlr.press/v63/lei63.pdf UR - https://proceedings.mlr.press/v63/lei63.html AB - We propose a localized approach to multiple kernel learning that can be formulated as a convex optimization problem over a given cluster structure. For which we obtain generalization error guarantees and derive an optimization algorithm based on the Fenchel dual representation. Experiments on real-world datasets from the application domains of computational biology and computer vision show that convex localized multiple kernel learning can achieve higher prediction accuracies than its global and non-convex local counterparts. ER -
APA
Lei, Y., Binder, A., Dogan, U. & Kloft, M.. (2016). Localized Multiple Kernel Learning—A Convex Approach. Proceedings of The 8th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 63:81-96 Available from https://proceedings.mlr.press/v63/lei63.html.

Related Material