Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Sterkenburg, Tom F.
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2312.13842
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913590582181888
author Sterkenburg, Tom F.
author_facet Sterkenburg, Tom F.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2312_13842
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Statistical learning theory and Occam's razor: The core argument
Sterkenburg, Tom F.
Machine Learning
Statistics Theory
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.
title Statistical learning theory and Occam's razor: The core argument
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2312.13842