Predictive Power of Nearest Neighbors Algorithm under Random Perturbation

Abstract

We consider a data corruption scenario in the classical $k$ Nearest Neighbors ($k$-NN) algorithm, that is, the testing data are randomly perturbed. Under such a scenario, the impact of corruption level on the asymptotic regret is carefully characterized. In particular, our theoretical analysis reveals a phase transition phenomenon that, when the corruption level $\omega$ is below a critical order (i.e., small-$\omega$ regime), the asymptotic regret remains the same; when it is beyond that order (i.e., large-$\omega$ regime), the asymptotic regret deteriorates polynomially. Surprisingly, we obtain a negative result that the classical noise-injection approach will not help improve the testing performance in the beginning stage of the large-$\omega$ regime, even in the level of the multiplicative constant of asymptotic regret. As a technical by-product, we prove that under different model assumptions, the pre-processed 1-NN proposed in \cite{xue2017achieving} will at most achieve a sub-optimal rate when the data dimension $d>4$ even if $k$ is chosen optimally in the pre-processing step.

References in corpus (8)

• Fast learning rates for plug-in classifiers
• Certifying Some Distributional Robustness with Principled Adversarial Training
• Fifty Years of Pulsar Candidate Selection: From simple filters to a new principled real-time classification approach
• Analyzing the Robustness of Nearest Neighbors to Adversarial Examples
• Rates of Convergence for Nearest Neighbor Classification
• Statistical Optimality of Interpolated Nearest Neighbor Algorithms
• Classification with unknown class-conditional label noise on non-compact feature spaces
• Achieving the time of $1$-NN, but the accuracy of $k$-NN