Non-Asymptotic Uniform Rates of Consistency for k-NN Regression
Machine Learning
2018-11-06 v2 Machine Learning
Abstract
We derive high-probability finite-sample uniform rates of consistency for -NN regression that are optimal up to logarithmic factors under mild assumptions. We moreover show that -NN regression adapts to an unknown lower intrinsic dimension automatically. We then apply the -NN regression rates to establish new results about estimating the level sets and global maxima of a function from noisy observations.
Keywords
Cite
@article{arxiv.1707.06261,
title = {Non-Asymptotic Uniform Rates of Consistency for k-NN Regression},
author = {Heinrich Jiang},
journal= {arXiv preprint arXiv:1707.06261},
year = {2018}
}
Comments
In Proceedings of 33rd AAAI Conference on Artificial Intelligence (AAAI 2019)