Localized Multiple Kernel Learning—A Convex Approach

Yunwen Lei, Alexander Binder, Urun Dogan, Marius Kloft

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

5 Citations (Scopus)


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.

Original languageEnglish
Title of host publicationJMLR
Subtitle of host publicationWorkshop and Conference Proceedings
EditorsRobert J. Durrant, Kee Eung Kim
Number of pages16
Publication statusPublished - Nov 2016
Event8th Asian Conference on Machine Learning, ACML 2016 - Hamilton, New Zealand
Duration: 16 Nov 201618 Nov 2016


Conference8th Asian Conference on Machine Learning, ACML 2016
Country/TerritoryNew Zealand

Scopus Subject Areas

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

User-Defined Keywords

  • Generalization analysis
  • Localized algorithms
  • Multiple kernel learning


Dive into the research topics of 'Localized Multiple Kernel Learning—A Convex Approach'. Together they form a unique fingerprint.

Cite this