Repository logo
 

The Mondrian Kernel

Accepted version
Peer-reviewed

Type

Article

Change log

Authors

Lakshminarayanan, B 
Roy, DM 
Teh, YW 

Abstract

We introduce the Mondrian kernel, a fast random feature approximation to the Laplace kernel. It is suitable for both batch and online learning, and admits a fast kernel-width-selection procedure as the random features can be re-used efficiently for all kernel widths. The features are constructed by sampling trees via a Mondrian process [Roy and Teh, 2009], and we highlight the connection to Mondrian forests [Lakshminarayanan et al., 2014], where trees are also sampled via a Mondrian process, but fit independently. This link provides a new insight into the relationship between kernel methods and random forests.

Description

Keywords

stat.ML, stat.ML

Journal Title

32nd Conference on Uncertainty in Artificial Intelligence (UAI 2016)

Conference Name

Journal ISSN

Volume Title

Publisher

Association for Uncertainty in Artificial Intelligence Press

Publisher DOI

Sponsorship
Gatsby Charitable Foundation, Alan Turing Institute, Google, Microsoft Research and Engineering and Physical Sciences Research Council (Grant ID: EP/N014162/1), NSERC (Discovery Grant), European Research Council under the European Union’s Seventh Framework Programme (FP7/2007-2013) (Grant agreement no. 617071)