Efficient Learning with Partially Observed Attributes
Abstract
We describe and analyze efficient algorithms for learning a linear predictor from examples when the learner can only view a few attributes of each training example. This is the case, for instance, in medical research, where each patient participating in the experiment is only willing to go through a small number of tests. Our analysis bounds the number of additional examples sufficient to compensate for the lack of full information on each training example. We demonstrate the efficiency of our algorithms by showing that when running on digit recognition data, they obtain a high prediction accuracy even when the learner gets to see only four pixels of each image.
Cite
Text
Cesa-Bianchi et al. "Efficient Learning with Partially Observed Attributes." International Conference on Machine Learning, 2010. doi:10.5555/1953048.2078197Markdown
[Cesa-Bianchi et al. "Efficient Learning with Partially Observed Attributes." International Conference on Machine Learning, 2010.](https://mlanthology.org/icml/2010/cesabianchi2010icml-efficient/) doi:10.5555/1953048.2078197BibTeX
@inproceedings{cesabianchi2010icml-efficient,
title = {{Efficient Learning with Partially Observed Attributes}},
author = {Cesa-Bianchi, Nicolò and Shalev-Shwartz, Shai and Shamir, Ohad},
booktitle = {International Conference on Machine Learning},
year = {2010},
pages = {183-190},
doi = {10.5555/1953048.2078197},
url = {https://mlanthology.org/icml/2010/cesabianchi2010icml-efficient/}
}