The covering number in learning theory
Journal of Complexity
Kernel Methods for Pattern Analysis
Kernel Methods for Pattern Analysis
Rates of convergence of nearest neighbor estimation under arbitrary sampling
IEEE Transactions on Information Theory
Hi-index | 754.84 |
Let F be a separable Banach space, and let (X, Y) be a random pair taking values in F × R. Motivated by a broad range of potential applications, we investigate rates of convergence of the k-nearest neighbor estimate rn(X) of the regression function r(X) = E[Y|X = X], based on n independent copies of the pair (X, Y). Using compact embedding theory, we present explicit and general finite sample bounds on the expected squared difference E[rn(X) - r(X)]2, and particularize our results to classical function spaces such as Sobolev spaces, Besov spaces, and reproducing kernel Hilbert spaces.