PAC Learning and Occam’s Razor: Probably Approximately Incorrect

Computer scientists have provided a distinct justification of Occam’s Razor. Using the probably approximately correct framework, they provide a theorem that they claim demonstrates that we should favor simpler hypotheses. The argument relies on a philosophical interpretation of the theorem. I argue...

Full description

Saved in:
Bibliographic Details
Published inPhilosophy of science Vol. 87; no. 4; pp. 685 - 703
Main Author Herrmann, Daniel A.
Format Journal Article
LanguageEnglish
Published Cambridge The University of Chicago Press 01.10.2020
Cambridge University Press
Subjects
Hypotheses
Justification
Learning
Theorems
Online AccessGet full text

Cover

More Information
Summary:Computer scientists have provided a distinct justification of Occam’s Razor. Using the probably approximately correct framework, they provide a theorem that they claim demonstrates that we should favor simpler hypotheses. The argument relies on a philosophical interpretation of the theorem. I argue that the standard interpretation of the result in the literature is misguided and that a better reading does not, in fact, support Occam’s Razor at all. To this end, I state and prove a very similar theorem that, if interpreted the same way, would justify the contradictory Anti-Occam’s Razor—the principle that we should favor more complex hypotheses.
ISSN:0031-8248
1539-767X
DOI:10.1086/709786