Analyzing sparse dictionaries for online learning with kernels
This work addresses theoretical challenges in sparse approximation for online learning with kernels, but it is incremental as it builds on existing sparsity measures without introducing new methods.
The paper analyzes sparse dictionaries for online kernel learning by examining sparsity measures like distance, approximation, coherence, and Babel, showing they share properties such as linear independence and well-posed optimization, and proves a quasi-isometry between parameter and feature spaces.
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.