arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1707.06261stat.MLcs.LG
收藏

k-NN回归的非渐近一致相合速度

Non-Asymptotic Uniform Rates of Consistency for k-NN Regression

Google Research(谷歌研究院)

Heinrich Jiang

摘要:

我们推导出$k$ -NN回归的一致性的高概率有限样本均匀速率,在温和的假设下,最佳的对数因子。此外,我们表明,$k$ -NN回归自动适应一个未知的较低的内在维数。然后,我们应用$k$ -NN回归率建立新的结果估计的水平集和全局最大值的一个函数从噪声的观察。

英文摘要:

We derive high-probability finite-sample uniform rates of consistency for $k$-NN regression that are optimal up to logarithmic factors under mild assumptions. We moreover show that $k$-NN regression adapts to an unknown lower intrinsic dimension automatically. We then apply the $k$-NN regression rates to establish new results about estimating the level sets and global maxima of a function from noisy observations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑