A Nearest Neighbor Characterization of Lebesgue Points in Metric Measure Spaces

2020/07/08 by Cesari, Tommaso, Colomboni, Roberto
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Probability (math.PR)

paper · doi:10.48550/arxiv.2007.03937

Abstract

The property of almost every point being a Lebesgue point has proven to be crucial for the consistency of several classification algorithms based on nearest neighbors. We characterize Lebesgue points in terms of a 1-Nearest Neighbor regression algorithm for pointwise estimation, fleshing out the role played by tie-breaking rules in the corresponding convergence problem. We then give an application of our results, proving the convergence of the risk of a large class of 1-Nearest Neighbor classification algorithms in general metric spaces where almost every point is a Lebesgue point.

Related

• Rates of Convergence for Nearest Neighbor Classification
• Classification with the nearest neighbor rule in general finite dimensional spaces: necessary and sufficient conditions
• Efficient Classification for Metric Data
• Metric Embedding for Nearest Neighbor Classification
• On L₂-consistency of nearest neighbor matching