Universal consistency of the k-NN rule in metric spaces and Nagata dimension

by   Benoît Collins, et al.
Kyoto University

The k nearest neighbour learning rule (under the uniform distance tie breaking) is universally consistent in every metric space X that is sigma-finite dimensional in the sense of Nagata. This was pointed out by Cérou and Guyader (2006) as a consequence of the main result by those authors, combined with a theorem in real analysis sketched by D. Preiss (1971) (and elaborated in detail by Assouad and Quentin de Gromard (2006)). We show that it is possible to give a direct proof along the same lines as the original theorem of Charles J. Stone (1977) about the universal consistency of the k-NN classifier in the finite dimensional Euclidean space. The generalization is non-trivial because of the distance ties being more prevalent in the non-euclidean setting, and on the way we investigate the relevant geometric properties of the metrics and the limitations of the Stone argument, by constructing various examples.


page 1

page 2

page 3

page 4


Universal consistency of the k-NN rule in metric spaces and Nagata dimension. II

We continue to investigate the k nearest neighbour learning rule in sepa...

Universal consistency of Wasserstein k-NN classifier

The Wasserstein distance provides a notion of dissimilarities between pr...

k-Nearest Neighbour Classification of Datasets with a Family of Distances

The k-nearest neighbour (k-NN) classifier is one of the oldest and most ...

Metric Embedding for Nearest Neighbor Classification

The distance metric plays an important role in nearest neighbor (NN) cla...

Topics in Random Matrices and Statistical Machine Learning

This thesis consists of two independent parts: random matrices, which fo...

Universal consistency and rates of convergence of multiclass prototype algorithms in metric spaces

We study universal consistency and convergence rates of simple nearest-n...

Is the k-NN classifier in high dimensions affected by the curse of dimensionality?

There is an increasing body of evidence suggesting that exact nearest ne...

Please sign up or login with your details

Forgot password? Click here to reset