Concentration bounds for intrinsic dimension estimation using Gaussian kernels
By: Martin Andersson
Potential Business Impact:
Helps computers guess how complex data is.
We prove finite-sample concentration and anti-concentration bounds for dimension estimation using Gaussian kernel sums. Our bounds provide explicit dependence on sample size, bandwidth, and local geometric and distributional parameters, characterizing precisely how regularity conditions govern statistical performance. We also propose a bandwidth selection heuristic using derivative information, which shows promise in numerical experiments.
Similar Papers
Nonparametric hazard rate estimation with associated kernels and minimax bandwidth choice
Statistics Theory
Helps predict when things will break.
Gaussian Approximation for High-Dimensional $U$-statistics with Size-Dependent Kernels
Statistics Theory
Helps math guess better with lots of data.
A general technique for approximating high-dimensional empirical kernel matrices
Machine Learning (Stat)
Makes computer predictions more accurate for complex data.