Material Detail

The Sample Complexity of Learning the Kernel

The Sample Complexity of Learning the Kernel

This video was recorded at NIPS Workshop on Kernel Learning: Automatic Selection of Optimal Kernels, Whistler 2008. The success of kernel based learning algorithms depends upon the suitability of the kernel to the learning task. Ideally, the choice of a kernel should based on prior information of the learner about the task at hand. However, in practice, kernel parameters are being tuned based on available training data. I will discuss the sample complexity overhead associated with such "learning the kernel" scenarios. I will address the setting in which the training data for the kernel selection is target labeled examples, as well as settings in which this training is based on different types of data, such as unlabeled examples and examples labeled by a different (but related) tasks. Part of this work is joint with Nati Srebro.


  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material


Log in to participate in the discussions or sign up if you are not already a MERLOT member.