Grid Point Approximation for Distributed Nonparametric Smoothing and Prediction

Abstract

Kernel smoothing is a widely used nonparametric method in modern statistical analysis. The problem of efficiently conducting kernel smoothing for a massive dataset on a distributed system is a problem of great importance. In this work, we find that the popularly used one-shot type estimator is highly inefficient for prediction purposes. To this end, we propose a novel grid point approximation (GPA) method, which has the following advantages. First, the resulting GPA estimator is as statistically efficient as the global estimator under mild conditions. Second, it requires no communication and is extremely efficient in terms of computation for prediction. Third, it is applicable to the case where the data are not randomly distributed across different machines. To select a suitable bandwidth, two novel bandwidth selectors are further developed and theoretically supported. Extensive numerical studies are conducted to corroborate our theoretical findings. Two real data examples are also provided to demonstrate the usefulness of our GPA method.

References in corpus (10)

• Variable selection in semiparametric regression modeling
• Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates
• Distributed learning with regularized least squares
• Least Squares Approximation for a Distributed System
• A review of distributed statistical inference
• Estimation of the covariance matrix of random effects in longitudinal studies
• Distributed Inference for Linear Support Vector Machine
• A Distributed and Integrated Method of Moments for High-Dimensional Correlated Data Analysis
• Computational Limits of A Distributed Algorithm For Smoothing Spline
• Doubly Distributed Supervised Learning and Inference with High-Dimensional Correlated Outcomes