Optimization Networks for Integrated Machine Learning

TL;DR

This paper explores the application of optimization networks to machine learning, demonstrating their flexibility and effectiveness in tasks like feature selection, model creation, and system optimization, offering a holistic approach to interrelated problems.

Contribution

It revisits the principles of optimization networks and adapts them for machine learning, showcasing their advantages over traditional methods through practical examples.

Findings

Optimization networks outperform ordinary least squares in feature selection.

They are adaptable for various machine learning tasks beyond initial benchmarks.

Optimization analysis benefits from the network's ability to handle model creation, selection, and parameter tuning.

Abstract

Optimization networks are a new methodology for holistically solving interrelated problems that have been developed with combinatorial optimization problems in mind. In this contribution we revisit the core principles of optimization networks and demonstrate their suitability for solving machine learning problems. We use feature selection in combination with linear model creation as a benchmark application and compare the results of optimization networks to ordinary least squares with optional elastic net regularization. Based on this example we justify the advantages of optimization networks by adapting the network to solve other machine learning problems. Finally, optimization analysis is presented, where optimal input values of a system have to be found to achieve desired output values. Optimization analysis can be divided into three subproblems: model creation to describe the system, model selection to choose the most appropriate one and parameter optimization to obtain the input values. Therefore, optimization networks are an obvious choice for handling optimization analysis tasks.