A Plea for History and Philosophy of Statistics and Machine Learning

2025-06-27

AI Summary

Contemporary historical and philosophical scholarship on statistics and machine learning lacks systematic integration, despite their accelerating convergence in the AI era. Method: This project pioneers an integrated approach combining history of science, philosophy of science, and formal epistemology—employing historical analysis (centered on the Neyman–Pearson framework), philosophical inquiry, and formal modeling to trace shared foundations. Contribution/Results: It introduces “attainabilism”: a novel methodological principle implicit in both frequentist statistics and machine learning practice—namely, prioritizing computationally feasible and empirically attainable objectives over absolute truth or asymptotic optimality. Attainabilism uncovers deep philosophical continuity between the disciplines, offering an original theoretical framework for methodological unification. By shifting focus from technical interoperability to epistemic alignment, the project advances statistics and machine learning toward a rigorous, cross-disciplinary epistemological dialogue.

Technology Category

• Machine Learning: Other Foundations of Machine Learning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Philosophy and Ethics of AI: AI & Epistemology

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Web Mining and Content Analysis: Machine learning and data science for the Web
• Security and Privacy: Security and privacy of machine learning and AI applications

Abstract

The integration of the history and philosophy of statistics was initiated at least by Hacking (1965) and advanced by Mayo (1996), but it has not received sustained follow-up. Yet such integration is more urgent than ever, as the recent success of artificial intelligence has been driven largely by machine learning -- a field historically developed alongside statistics. Today, the boundary between statistics and machine learning is increasingly blurred. What we now need is integration, twice over: of history and philosophy, and of the field they engage -- statistics and machine learning. I present a case study of a philosophical idea in machine learning (and in formal epistemology) whose root can be traced back to an often under-appreciated insight in Neyman and Pearson's 1936 work (a follow-up to their 1933 classic). This leads to the articulation of a foundational assumption -- largely implicit in, but shared by, the practices of frequentist statistics and machine learning -- which I call achievabilism. Another integration also emerges at the level of methodology, combining two ends of the philosophy of science spectrum: history and philosophy of science on the one hand, and formal epistemology on the other hand.

Problem

• Integrating history and philosophy of statistics and machine learning
• Clarifying the blurred boundary between statistics and machine learning
• Articulating foundational assumptions in frequentist statistics and machine learning

Innovation

• Integrates history and philosophy of statistics
• Links machine learning to Neyman-Pearson insights
• Combines history of science with formal epistemology