Joint Kernel Maps

Jason Weston, Bernhard Schoelkopf, Olivier Bousquet, Tobias Mann and William Stafford Noble


Abstract

We develop a methodology for solving high dimensional dependency estimation problems between pairs of data types, which is viable in the case where the output of interest has very high dimension, e.g. thousands of dimensions. This is achieved by mapping the objects into continuous or discrete spaces, using joint kernels. Known correlations between input and output can be defined by such kernels, some of which can maintain linearity in the outputs to provide simple (closed form) pre-images. We provide examples of such kernels and empirical results on mass spectrometry prediction and mapping between images.
Download article
Supplementary Experiments (artificial data, digit reconstruction)
View full image mapping (smiling face) results