Towards Linearization Machine Learning Algorithms

TL;DR

This paper introduces a multilinear projection-based machine learning approach that transforms prediction tasks into consensus problems among nearest neighbors in a linear space, showing improved accuracy over existing methods.

Contribution

It proposes a novel multilinear projection method for regression and classification, with implementations demonstrating superior accuracy compared to standard Spark MLlib algorithms.

Findings

Improved prediction accuracy over existing Spark MLlib algorithms.

Effective for both regression and binary classification tasks.

Validated on multiple LIBSVM datasets.

Abstract

This paper is about a machine learning approach based on the multilinear projection of an unknown function (or probability distribution) to be estimated towards a linear (or multilinear) dimensional space E'. The proposal transforms the problem of predicting the target of an observation x into a problem of determining a consensus among the k nearest neighbors of x's image within the dimensional space E'. The algorithms that concretize it allow both regression and binary classification. Implementations carried out using Scala/Spark and assessed on a dozen LIBSVM datasets have demonstrated improvements in prediction accuracies in comparison with other prediction algorithms implemented within Spark MLLib such as multilayer perceptrons, logistic regression classifiers and random forests.