Almost Optimal Proper Learning and Testing Polynomials
Machine Learning
2022-02-08 v1 Data Structures and Algorithms
Machine Learning
Abstract
We give the first almost optimal polynomial-time proper learning algorithm of Boolean sparse multivariate polynomial under the uniform distribution. For -sparse polynomial over variables and , , our algorithm makes queries. Notice that our query complexity is sublinear in and almost linear in . All previous algorithms have query complexity at least quadratic in and linear in . We then prove the almost tight lower bound Applying the reduction in~\cite{Bshouty19b} with the above algorithm, we give the first almost optimal polynomial-time tester for -sparse polynomial. Our tester, for , makes queries.
Cite
@article{arxiv.2202.03207,
title = {Almost Optimal Proper Learning and Testing Polynomials},
author = {Nader H. Bshouty},
journal= {arXiv preprint arXiv:2202.03207},
year = {2022}
}