Adaptivity to Local Smoothness and Dimension in Kernel Regression

Part of Advances in Neural Information Processing Systems 26 (NIPS 2013)

Bibtex »Metadata »Paper »Reviews »

Authors

Samory Kpotufe, Vikas Garg

Abstract

We present the first result for kernel regression where the procedure adapts locally at a point $x$ to both the unknown local dimension of the metric and the unknown H\{o}lder-continuity of the regression function at $x$. The result holds with high probability simultaneously at all points $x$ in a metric space of unknown structure."