Local statistical modeling by cluster-weighted

TL;DR

This paper explores the statistical properties of Cluster-Weighted Modeling, a flexible framework for local supervised learning, comparing it with finite mixture models through theoretical analysis and simulations.

Contribution

It demonstrates that Cluster-Weighted Modeling offers a more general approach for local statistical modeling compared to traditional finite mixture models.

Findings

Cluster-Weighted Modeling is more flexible than finite mixture models.

Theoretical insights are supported by numerical simulations.

The framework is applicable to supervised learning tasks.

Abstract

We investigate statistical properties of Cluster-Weighted Modeling, which is a framework for supervised learning originally developed in order to recreate a digital violin with traditional inputs and realistic sound. The analysis is carried out in comparison with Finite Mixtures of Regression models. Based on some geometrical arguments, we highlight that Cluster-WeightedModeling provides a quite general framework for local statistical modeling. Theoretical results are illustrated on the ground of some numerical simulations.