Supervised Machine Learning with a Novel Pointwise Density Estimator

TL;DR

This paper introduces a new density estimation algorithm for supervised machine learning that is computationally efficient and potentially more accurate than kernel density estimation methods, especially suitable for large datasets.

Contribution

It presents a novel pointwise density estimator-based algorithm with linear time complexity, not relying on infinite sample assumptions, improving prediction accuracy in some cases.

Findings

O(n) classifier generation time

Potentially higher accuracy than kernel methods

Effective for large datasets

Abstract

This article proposes a novel density estimation based algorithm for carrying out supervised machine learning. The proposed algorithm features O(n) time complexity for generating a classifier, where n is the number of sampling instances in the training dataset. This feature is highly desirable in contemporary applications that involve large and still growing databases. In comparison with the kernel density estimation based approaches, the mathe-matical fundamental behind the proposed algorithm is not based on the assump-tion that the number of training instances approaches infinite. As a result, a classifier generated with the proposed algorithm may deliver higher prediction accuracy than the kernel density estimation based classifier in some cases.