A Scalable Algorithm for Structured Kernel Feature Selection
Shaogang Ren, Shuai Huang, John Onofrey, Xenios Papademetris, Xiaoning Qian
Abstract
Kernel methods are powerful tools for nonlinear feature representation. Incorporated with structured LASSO, the kernelized structured LASSO is an effective feature selection approach that can preserve the nonlinear input-output relationships as well as the structured sparseness. But as the data dimension increases, the method can quickly become computationally prohibitive. In this paper we propose a stochastic optimization algorithm that can efficiently address this computational problem on account of the redundant kernel representations of the given data. Experiments on simulation data and PET 3D brain image data show that our method can achieve superior accuracy with less computational cost than existing methods.
BibTeX
@InProceedings{pmlr-v38-ren15,
title = {{A Scalable Algorithm for Structured Kernel Feature Selection}},
author = {Ren, Shaogang and Huang, Shuai and Onofrey, John and Papademetris, Xenios and Qian, Xiaoning},
booktitle = {Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics},
pages = {781--789},
year = {2015},
editor = {Lebanon, Guy and Vishwanathan, S. V. N.},
volume = {38},
series = {Proceedings of Machine Learning Research},
address = {San Diego, California, USA},
month = {09--12 May},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v38/ren15.pdf},
url = {https://proceedings.mlr.press/v38/ren15.html},
abstract = {Kernel methods are powerful tools for nonlinear feature representation. Incorporated with structured LASSO, the kernelized structured LASSO is an effective feature selection approach that can preserve the nonlinear input-output relationships as well as the structured sparseness. But as the data dimension increases, the method can quickly become computationally prohibitive. In this paper we propose a stochastic optimization algorithm that can efficiently address this computational problem on account of the redundant kernel representations of the given data. Experiments on simulation data and PET 3D brain image data show that our method can achieve superior accuracy with less computational cost than existing methods.}
}