Second Order Cone Programming Approaches for Handling Missing and Uncertain Data
Abstract
We propose a novel second order cone programming formulation for designing robust classifiers which can handle uncertainty in observations. Similar formulations are also derived for designing regression functions which are robust to uncertainties in the regression setting. The proposed formulations are independent of the underlying distribution, requiring only the existence of second order moments. These formulations are then specialized to the case of missing values in observations for both classification and regression problems. Experiments show that the proposed formulations outperform imputation.
Cite
Text
Shivaswamy et al. "Second Order Cone Programming Approaches for Handling Missing and Uncertain Data." Journal of Machine Learning Research, 2006.Markdown
[Shivaswamy et al. "Second Order Cone Programming Approaches for Handling Missing and Uncertain Data." Journal of Machine Learning Research, 2006.](https://mlanthology.org/jmlr/2006/shivaswamy2006jmlr-second/)BibTeX
@article{shivaswamy2006jmlr-second,
title = {{Second Order Cone Programming Approaches for Handling Missing and Uncertain Data}},
author = {Shivaswamy, Pannagadatta K. and Bhattacharyya, Chiranjib and Smola, Alexander J.},
journal = {Journal of Machine Learning Research},
year = {2006},
pages = {1283-1314},
volume = {7},
url = {https://mlanthology.org/jmlr/2006/shivaswamy2006jmlr-second/}
}