• Paper
• Source Code
• Data Sets
• References

The Paper

• The paper can be downloaded here: [pdf] [bibtex]

Source Code

• Implementations of various MKL formulations including the proposed Lp-norm-MKL formulation can be found in the Shogun Toolbox. The toolbox comes with examples that explain the usage of the MKL implementations:
  
  http://www.shogun-toolbox.org/doc/en/current/examples.html
• Additional matlab wrapper scripts for Shogun-based MKL training/testing (including validation): matlab_scripts.zip
• Code to reproduce the experiments: experiments.tar.gz

Datasets

• Runtime experiment on MNIST data
• Toy experiment
• Subcellular localization experiment
• Splice site detection experiment: training data, test data
• Metabolic experiment (data obtained from K. Bleakley's homepage)

References

[1] Marius Kloft, Ulf Brefeld, Sören Sonnenburg, and Alexander Zien. 
    Lp-Norm Multiple Kernel Learning. Journal of Machine Learning Research 
    (JMLR), 12:953--997, 2011.

[2] Marius Kloft, Ulf Brefeld, Sören Sonnenburg, Pavel Laskov, Klaus-Robert
    Müller, and Alexander Zien. Efficient and Accurate Lp-Norm Multiple Kernel
    Learning. In Y. Bengio and D. Schuurmans and J. Lafferty and C. K. I. Williams
    and A. Culotta, editor, In Advances in Neural Information Processing Systems 22, 
    pages 997-1005, MIT Press, 2009.