Metraipolis › archive › dc_9967734fe478

No free lunch theorem — Wikipedia (en)

Source: Wikipedia (en)
Original: https://en.wikipedia.org/wiki/No_free_lunch_theorem
License (as archived): CC-BY-SA-4.0
Archived: 2026-10-15T18:43:09.100Z
SHA-256 of the archived text: c3787b8360ccd4dd5cf2972d630f7f637eafbe5dc919c63902fd0fd8fbf3a8cf
Stable URL of this page: https://metraipolis.com/documento/dc_9967734fe478

How to cite

No free lunch theorem — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/No_free_lunch_theorem (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_9967734fe478 (Metraipolis archive dc_9967734fe478, sha256 c3787b8360ccd4dd5cf2972d630f7f637eafbe5dc919c63902fd0fd8fbf3a8cf)

BibTeX

@misc{dc9967734fe478,
  title = {No free lunch theorem — Wikipedia (en)},
  howpublished = {Wikipedia (en)},
  url = {https://en.wikipedia.org/wiki/No_free_lunch_theorem},
  note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_9967734fe478; sha256 c3787b8360ccd4dd5cf2972d630f7f637eafbe5dc919c63902fd0fd8fbf3a8cf},
  year = {2026}
}

Archived text

Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/No_free_lunch_theorem. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In mathematical folklore, the "no free lunch" (NFL) theorem (sometimes pluralized) of David Wolpert and William Macready, alludes to the saying "no such thing as a free lunch". In this case the intended meaning is that on the average there are no easy shortcuts to designing optimization algorithms. It appeared in the 1997 paper "No Free Lunch Theorems for Optimization". Wolpert had previously derived no free lunch theorems for machine learning. In 2005, Wolpert and Macready stated that the first theorem in their paper means that "any two optimization algorithms are equivalent when their performance is averaged across all possible problems". The "no free lunch" (NFL) theorem is an easily stated and easily understood consequence of theorems Wolpert and Macready actually prove. It is objectively weaker than the proven theorems, and thus does not encapsulate them. Various investigators have extended the work of Wolpert and Macready substantively. In terms of how the NFL theorem is used in the context of the research area, the no free lunch in search and optimization is a field that is dedicated for purposes of mathematically analyzing data for statistical identity, particularly search and optimization. While some scholars argue that NFL conveys important insight, others argue that NFL is of little relevance to machine learning research.

Tema degli esploratori: storia e filosofia della scienza (deposito sistematico; ricerca «scientific method»).
Fonte: Wikipedia in inglese, voce «No free lunch theorem» — https://en.wikipedia.org/wiki/No_free_lunch_theorem
Wikidata Q7045226 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q7045226
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/No_free_lunch_theorem?action=history).
Licenza: Creative Commons Attribuzione-Condividi allo stesso modo 4.0 (CC BY-SA 4.0) — https://creativecommons.org/licenses/by-sa/4.0/. Il riuso richiede attribuzione e stessa licenza.
Estratto dell'introduzione non modificato nel contenuto; revisione 1377469694, consultata il 2026-10-15T18:07:12.853Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 74bef189039ab5f97452a4cfe5d78320b216a8cc8a6752e90123ea88437360d9