k-NN Regression Adapts to Local Intrinsic Dimension

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.

[1]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[2]  Trevor Darrell,et al.  Nearest-Neighbor Searching and Metric Space Dimensions , 2006 .

[3]  Adam Krzyzak,et al.  A Distribution-Free Theory of Nonparametric Regression , 2002, Springer series in statistics.

[4]  Samory Kpotufe,et al.  Fast, smooth and adaptive regression in metric spaces , 2009, NIPS.

[5]  J. Mixter.  Fast , 2012 .

[6]  C. J. Stone,et al.  Optimal Rates of Convergence for Nonparametric Estimators , 1980 .

[7]  R. Cao-Abad,et al.  Rate of Convergence for the Wild Bootstrap in Nonparametric Regression , 1991 .

[8]  E. Saksman,et al.  Every complete doubling metric space carries a doubling measure , 1998 .

[9]  Samory Kpotufe,et al.  Escaping the Curse of Dimensionality with a Tree-based Regressor , 2009, COLT.

[10]  H. Fédérer.  Geometric Measure Theory , 1969 .

[11]  C. J. Stone,et al.  OPTIMAL GLOBAL RATES OF CONVERGENCE FOR NONPARAMETRIC ESTIMATORS , 1982 .

[12]  J. Staniswalis.  Local Bandwidth Selection for Kernel Estimates , 1989 .

[13]  P. Bickel,et al.  Local polynomial regression on unknown manifolds , 2007, 0708.0983.

[14]  C. D. Cutler,et al.  A REVIEW OF THE THEORY AND ESTIMATION OF FRACTAL DIMENSION , 1993 .

[15]  I. Holopainen.  Riemannian Geometry , 1927, Nature.

[16]  Sanjeev R. Kulkarni,et al.  Rates of convergence of nearest neighbor estimation under arbitrary sampling , 1995, IEEE Trans. Inf. Theory.

[17]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[18]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[19]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.