Multiple Kernel Learning: A Unifying Probabilistic Viewpoint


Technical Report


We present a probabilistic viewpoint to multiple kernel learning unifying well-known regularised risk approaches and recent advances in approximate Bayesian inference relaxations. The framework proposes a general objective function suitable for regression, robust regression and classification that is lower bound of the marginal likelihood and contains many regularised risk approaches as special cases. Furthermore, we derive an efficient and provably convergent optimisation algorithm.

Author(s): Nickisch, H. and Seeger, M.
Year: 2011
Month: March
Day: 0

Department(s): Empirical Inference
Bibtex Type: Technical Report (techreport)

Institution: Max Planck Institute for Biological Cybernetics

Digital: 0

Links: Web


  title = {Multiple Kernel Learning: A Unifying Probabilistic Viewpoint},
  author = {Nickisch, H. and Seeger, M.},
  institution = {Max Planck Institute for Biological Cybernetics},
  month = mar,
  year = {2011},
  month_numeric = {3}