Timezone: »

An Empirical Study on The Properties of Random Bases for Kernel Methods
Maximilian Alber · Pieter-Jan Kindermans · Kristof Schütt · Klaus-Robert Müller · Fei Sha

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #65

Kernel machines as well as neural networks possess universal function approximation properties. Nevertheless in practice their ways of choosing the appropriate function class differ. Specifically neural networks learn a representation by adapting their basis functions to the data and the task at hand, while kernel methods typically use a basis that is not adapted during training. In this work, we contrast random features of approximated kernel machines with learned features of neural networks. Our analysis reveals how these random and adaptive basis functions affect the quality of learning. Furthermore, we present basis adaptation schemes that allow for a more compact representation, while retaining the generalization properties of kernel machines.

Author Information

Maximilian Alber (TU Berlin)
Pieter-Jan Kindermans (Google Brain)
Kristof Schütt (TU Berlin)
Klaus-Robert Müller (TU Berlin)
Fei Sha (University of Southern California (USC))

More from the Same Authors