Skip to Main content Skip to Navigation
Journal articles

Analyzing sparse dictionaries for online learning with kernels

Paul Honeine 1 
Abstract : Many signal processing and machine learning methods share essentially the same linear-in-the-parameter model, with as many parameters as available samples as in kernel-based machines. Sparse approximation is essential in many disciplines, with new challenges emerging in online learning with kernels. To this end, several sparsity measures have been proposed in the literature to quantify sparse dictionaries and constructing relevant ones, the most prolific ones being the distance, the approximation, the coherence and the Babel measures. In this paper, we analyze sparse dictionaries based on these measures. By conducting an eigenvalue analysis, we show that these sparsity measures share many properties, including the linear independence condition and inducing a well-posed optimization problem. Furthermore, we prove that there exists a quasi-isometry between the parameter (i.e., dual) space and the dictionary's induced feature space.
Complete list of metadata

Cited literature [62 references]  Display  Hide  Download
Contributor : Paul Honeine Connect in order to contact the contributor
Submitted on : Wednesday, December 26, 2018 - 12:53:19 PM
Last modification on : Wednesday, August 31, 2022 - 6:56:38 PM
Long-term archiving on: : Wednesday, March 27, 2019 - 12:48:26 PM


Files produced by the author(s)




Paul Honeine. Analyzing sparse dictionaries for online learning with kernels. IEEE Transactions on Signal Processing, Institute of Electrical and Electronics Engineers, 2015, 63 (23), pp.6343 - 6353. ⟨10.1109/TSP.2015.2457396⟩. ⟨hal-01965568⟩



Record views


Files downloads