Active Sampling for Multiple Output Identification
Abstract
We study functions with multiple output values, and use active sampling to identify an example for each of the possible output values. Our results for this setting include: (1) Efficient active sampling algorithms for simple geometric concepts, such as intervals on a line and axis parallel boxes. (2) A characterization for the case of binary output value in a transductive setting. (3) An analysis of active sampling with uniform distribution in the plane. (4) An efficient algorithm for the Boolean hypercube when each output value is a monomial.
Cite
Text
Fine and Mansour. "Active Sampling for Multiple Output Identification." Annual Conference on Computational Learning Theory, 2006. doi:10.1007/11776420_45Markdown
[Fine and Mansour. "Active Sampling for Multiple Output Identification." Annual Conference on Computational Learning Theory, 2006.](https://mlanthology.org/colt/2006/fine2006colt-active/) doi:10.1007/11776420_45BibTeX
@inproceedings{fine2006colt-active,
title = {{Active Sampling for Multiple Output Identification}},
author = {Fine, Shai and Mansour, Yishay},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2006},
pages = {620-634},
doi = {10.1007/11776420_45},
url = {https://mlanthology.org/colt/2006/fine2006colt-active/}
}