k-NN回归适应于局部固有维数k-NN Regression Adapts to Local Intrinsic Dimension |
|
课程网址: | http://videolectures.net/nips2011_kpotufe_intrinsic/ |
主讲教师: | Samory Kpotufe |
开课单位: | 普林斯顿大学 |
开课时间: | 2012-01-25 |
课程语种: | 英语 |
中文简介: | 最近显示许多非参数回归量的收敛速度仅取决于数据的内在维度。因此,当高维数据具有低内在尺寸(例如,歧管)时,这些回归量摆脱了维度的诅咒。我们证明$ k $ NN回归也适应内在维度。特别是我们的费率是查询$ x $的本地费率,并且仅取决于以$ x $为中心的球的质量随半径而变化的方式。此外,我们展示了一种在任何$ x $选择$ k = k(x)$本地的简单方法,以便在$ x $附近的未知内在维度方面几乎达到$ x $的最小极大率。我们还确定最小极大速率不依赖于度量空间或分布的特定选择,而是该最小极大速率适用于任何度量空间和倍增度量。 |
课程简介: | Many nonparametric regressors were recently shown to converge at rates that depend only on the intrinsic dimension of data. These regressors thus escape the curse of dimension when high-dimensional data has low intrinsic dimension (e.g. a manifold). We show that $k$-NN regression is also adaptive to intrinsic dimension. In particular our rates are local to a query $x$ and depend only on the way masses of balls centered at $x$ vary with radius. Furthermore, we show a simple way to choose $k = k(x)$ locally at any $x$ so as to nearly achieve the minimax rate at $x$ in terms of the unknown intrinsic dimension in the vicinity of $x$. We also establish that the minimax rate does not depend on a particular choice of metric space or distribution, but rather that this minimax rate holds for any metric space and doubling measure. |
关 键 词: | 非参数回归量; 高维数据; 内在维度 |
课程来源: | 视频讲座网 |
最后编审: | 2019-09-06:lxf |
阅读次数: | 73 |