Learning Real Polynomials with a Turing Machine
Abstract
We provide an algorithm to PAC learn multivariate polynomials with real coefficients. The instance space from which labeled samples are drawn is IR^N but the coordinates of such samples are known only approximately. The algorithm is iterative and the main ingredient of its complexity, the number of iterations it performs, is estimated using the condition number of a linear programming problem associated to the sample. To the best of our knowledge, this is the first study of PAC learning concepts parameterized by real numbers from approximate data.
Cite
Text
Cheung. "Learning Real Polynomials with a Turing Machine." International Conference on Algorithmic Learning Theory, 1999. doi:10.1007/3-540-46769-6_19Markdown
[Cheung. "Learning Real Polynomials with a Turing Machine." International Conference on Algorithmic Learning Theory, 1999.](https://mlanthology.org/alt/1999/cheung1999alt-learning/) doi:10.1007/3-540-46769-6_19BibTeX
@inproceedings{cheung1999alt-learning,
title = {{Learning Real Polynomials with a Turing Machine}},
author = {Cheung, Dennis},
booktitle = {International Conference on Algorithmic Learning Theory},
year = {1999},
pages = {231-240},
doi = {10.1007/3-540-46769-6_19},
url = {https://mlanthology.org/alt/1999/cheung1999alt-learning/}
}