Analyzing Sparse Dictionaries for Online Learning With Kernels

DOI10.1109/TSP.2015.2457396MaRDI QIDQ4580941zbMATH OpenOpenAlexFDO

Authors Paul Honeine

Publication date 22 August 2018

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1409.6045

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

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.

Cited in

(5)

• Online learning for matrix factorization and sparse coding
• Online Dictionary Learning for Kernel LMS
• Correlation Based Online Dictionary Learning Algorithm
• scientific article; zbMATH DE number 7626711 (Why is no real title available?)
• Kernelized elastic net regularization: generalization bounds, and sparse recovery

This page was built for publication: Analyzing Sparse Dictionaries for Online Learning With Kernels

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4580941)