On the size of the online kernel sparsification dictionary

Yi Sun, Faustino Gomez, Jürgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Scopus citations

Abstract

We analyze the size of the dictionary constructed from online kernel sparsification, using a novel formula that expresses the expected determinant of the kernel Gram matrix in terms of the eigenvalues of the covariance operator. Using this formula, we are able to connect the cardinality of the dictionary with the eigen-decay of the covariance operator. In particular, we show that under certain technical conditions, the size of the dictionary will always grow sub-linearly in the number of data points, and, as a consequence, the kernel linear regressor constructed from the resulting dictionary is consistent. Copyright 2012 by the author(s)/owner(s).
Original languageEnglish (US)
Title of host publicationProceedings of the 29th International Conference on Machine Learning, ICML 2012
Pages329-336
Number of pages8
StatePublished - Oct 10 2012
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2022-09-14

Fingerprint

Dive into the research topics of 'On the size of the online kernel sparsification dictionary'. Together they form a unique fingerprint.

Cite this