Statistical Learning Theory and Occam’s Razor: The Core Argument

Sterkenburg, Tom F. (27. November 2024): Statistical Learning Theory and Occam’s Razor: The Core Argument. In: Minds and Machines, Bd. 35, 3

Abstract

Statistical learning theory is often associated with the principle of Occam’s razor, which recommends a simplicity preference in inductive inference. This paper distills the core argument for simplicity obtainable from statistical learning theory, built on the theory’s central learning guarantee for the method of empirical risk minimization. This core “means-ends” argument is that a simpler hypothesis class or inductive model is better because it has better learning guarantees; however, these guarantees are model-relative and so the theoretical push towards simplicity is checked by our prior knowledge.

• Dokumententyp: Zeitschriftenartikel
• Fakultät: Philosophie, Wissenschaftstheorie und Religionswissenschaft > Munich Center for Mathematical Philosophy (MCMP)
• Themengebiete: 100 Philosophie und Psychologie > 100 Philosophie ; 500 Naturwissenschaften und Mathematik > 510 Mathematik
• ISSN: 1572-8641
• Sprache: Englisch