NeurIPS 2018spotlight70 citations

Quadrature-based features for kernel approximation

Marina Munkhoeva, Yermek Kapushev, Evgeny Burnaev, Ivan Oseledets

Abstract

We consider the problem of improving kernel approximation via randomized feature maps. These maps arise as Monte Carlo approximation to integral representations of kernel functions and scale up kernel methods for larger datasets. Based on an efficient numerical integration technique, we propose a unifying approach that reinterprets the previous random features methods and extends to better estimates of the kernel approximation. We derive the convergence behavior and conduct an extensive empirical study that supports our hypothesis.

BibTeX
@inproceedings{NEURIPS2018_6e923226,
 author = {Munkhoeva, Marina and Kapushev, Yermek and Burnaev, Evgeny and Oseledets, Ivan},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Quadrature-based features for kernel approximation},
 url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/6e923226e43cd6fac7cfe1e13ad000ac-Paper.pdf},
 volume = {31},
 year = {2018}
}