Metraipolis › archive › dc_8dc4b445f068

Statistical learning theory and Occam's razor: Regularization — arXiv:2608.04049

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04049
License (as archived)
CC0-1.0
Archived
2026-10-31T11:35:36.928Z
SHA-256 of the archived text
d7aaafb2e5e07df1af2ba0b22f53f4d8d4c52824b2c7c68dd7f9dbe1b9258d76
Stable URL of this page
https://metraipolis.com/documento/dc_8dc4b445f068

How to cite

Statistical learning theory and Occam's razor: Regularization — arXiv:2608.04049 — arXiv (en), https://arxiv.org/abs/2608.04049 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8dc4b445f068 (Metraipolis archive dc_8dc4b445f068, sha256 d7aaafb2e5e07df1af2ba0b22f53f4d8d4c52824b2c7c68dd7f9dbe1b9258d76)
BibTeX
@misc{dc8dc4b445f068,
  title = {Statistical learning theory and Occam's razor: Regularization — arXiv:2608.04049},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04049},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8dc4b445f068; sha256 d7aaafb2e5e07df1af2ba0b22f53f4d8d4c52824b2c7c68dd7f9dbe1b9258d76},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04049. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The principle of Occam's razor, which instructs us to prefer simplicity in inductive inference, has attracted much scrutiny both in the philosophy of science and in machine learning. In either field, however, a justification for the principle has been elusive. In this paper, building on an earlier "core argument," I spell out a justification from statistical learning theory for the procedure of regularization: for trading off fit for simplicity. The means-ends argument is that in order to profit from theoretical reliability and "what-you-see-is-what-you-get" guarantees, one must implement a certain preference for simplicity over fit. This is a genuine methodological justification, which neither collapses to a purely pragmatic principle that we prefer simplicity for its own sake, nor to an ontological assumption that the truth is simple.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.04049 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T11:24:48.819Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).