Design Principles for Falsifiable, Replicable and Reproducible Empirical ML Research

TL;DR

This paper proposes a comprehensive model and guidelines to improve the consistency, reliability, and impact of empirical machine learning research by emphasizing clear hypotheses, precise experiment execution, and rigorous statistical analysis.

Contribution

It introduces a structured model for empirical ML research and provides guidelines to enhance research validity and reproducibility.

Findings

A new model for empirical research process in ML

Guidelines to improve research validity and reproducibility

Expected increase in research reliability and impact

Abstract

Empirical research plays a fundamental role in the machine learning domain. At the heart of impactful empirical research lies the development of clear research hypotheses, which then shape the design of experiments. The execution of experiments must be carried out with precision to ensure reliable results, followed by statistical analysis to interpret these outcomes. This process is key to either supporting or refuting initial hypotheses. Despite its importance, there is a high variability in research practices across the machine learning community and no uniform understanding of quality criteria for empirical research. To address this gap, we propose a model for the empirical research process, accompanied by guidelines to uphold the validity of empirical research. By embracing these recommendations, greater consistency, enhanced reliability and increased impact can be achieved.