Feature Space Perspectives for Learning the Kernel
Abstract
In this paper, we continue our study of learning an optimal kernel in a prescribed convex set of kernels (Micchelli & Pontil, 2005) . We present a reformulation of this problem within a feature space environment. This leads us to study regularization in the dual space of all continuous functions on a compact domain with values in a Hilbert space with a mix norm. We also relate this problem in a special case to ${\cal L}^p$ regularization.
Cite
Text
Micchelli and Pontil. "Feature Space Perspectives for Learning the Kernel." Machine Learning, 2007. doi:10.1007/S10994-006-0679-0Markdown
[Micchelli and Pontil. "Feature Space Perspectives for Learning the Kernel." Machine Learning, 2007.](https://mlanthology.org/mlj/2007/micchelli2007mlj-feature/) doi:10.1007/S10994-006-0679-0BibTeX
@article{micchelli2007mlj-feature,
title = {{Feature Space Perspectives for Learning the Kernel}},
author = {Micchelli, Charles A. and Pontil, Massimiliano},
journal = {Machine Learning},
year = {2007},
pages = {297-319},
doi = {10.1007/S10994-006-0679-0},
volume = {66},
url = {https://mlanthology.org/mlj/2007/micchelli2007mlj-feature/}
}