Is Ockham’s razor losing its edge? New perspectives on the principle of model parsimony

2025/01/27 by Marina Dubova, Suyog Chandramouli, Gerd Gigerenzer +12 · 2 voices · 24 citations
Computer Science · Decision Sciences · Mathematics · #Artificial intelligence #Biology #Computer science #Context (archaeology) #Data Visualization and Analytics #Data science #Epistemology #Explainable Artificial Intelligence (XAI) #Interpretability #Management science #Mathematics #Occam's razor #Paleontology #Scientific Computing and Data Management #Scientific modelling #Simple (philosophy) #Statistics

paper · pdf · doi:10.1073/pnas.2401230121

published in Proceedings of the National Academy of Sciences 122(5), e2401230121 (National Academy of Sciences)

openalex publication_date 2025/01/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06

Abstract

The preference for simple explanations, known as the parsimony principle, has long guided the development of scientific theories, hypotheses, and models. Yet recent years have seen a number of successes in employing highly complex models for scientific inquiry (e.g., for 3D protein folding or climate forecasting). In this paper, we reexamine the parsimony principle in light of these scientific and technological advancements. We review recent developments, including the surprising benefits of modeling with more parameters than data, the increasing appreciation of the context-sensitivity of data and misspecification of scientific models, and the development of new modeling tools. By integrating these insights, we reassess the utility of parsimony as a proxy for desirable model traits, such as predictive accuracy, interpretability, effectiveness in guiding new research, and resource efficiency. We conclude that more complex models are sometimes essential for scientific progress, and discuss the ways in which parsimony and complexity can play complementary roles in scientific modeling practice.

Citations

• On the Dangers of Stochastic Parrots
• Why the simplest explanation isn’t always the best
• Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)
• Estimating the Dimension of a Model

Cited by

• Integrative experiments identify how punishment affects welfare in public goods games
• The “5L” framework of diagnostic reasoning: A stepwise scaffold to support clinician educators
• Imagining and building wise machines: the centrality of AI metacognition
• A generative model of function growth explains hidden self-similarities across biological and social systems
• TinyTim: A Family of Language Models for Divergent Generation
• Representative, Informative, and De-Amplifying: Requirements for Robust Bayesian Active Learning under Model Misspecification
• Statistical learning theory and Occam's razor: Regularization
• Model fit vs. predictive reliability: a case study of the 1978 influenza outbreak. [europepmc]
• Video game engines as the new "virtual" Skinner box. [europepmc]
• Lack of group-to-individual generalizability in pseudocontingencies. [europepmc]
• People Evaluate Agents Based on the Algorithms That Drive Their Behavior. [europepmc]
• Dialogues about the practice of science. [europepmc]

Discussions

• Important piece on the role of Ockham's razor in the modern world of scientific modeling in @pnas.org. Conclusion: Complex models can be quite useful, and parsimony and complexity can complement each [bsky, 46 points, 3 comments]
• A colleague with whom I discuss science philosophy, @rachelglade.bsky.social, sent this recent PNAS article. It's worth reading. But if you are tuned to the hard sciences, notably physics, there are s [bsky, 2 points, 1 comments]

Related

• Is Ockham’s razor losing its edge? New perspectives on the principle of model parsimony
• Parsimony in Model Selection: Tools for Assessing Fit Propensity
• Model Pluralism
• Model Pluralism
• Breiman's two cultures: You don't have to choose sides