Metraipolis › archive › dc_3d46e26fa4f0

Evidence lower bound — Wikipedia (en)

Source
Wikipedia (en)
Original
https://en.wikipedia.org/wiki/Evidence_lower_bound
License (as archived)
CC-BY-SA-4.0
Archived
2026-10-07T20:41:16.054Z
SHA-256 of the archived text
2a17668c71f0f663dbccb5905ced2547af4b6d82d7c0a292810c6c73c55482f0
Stable URL of this page
https://metraipolis.com/documento/dc_3d46e26fa4f0

How to cite

Evidence lower bound — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Evidence_lower_bound (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_3d46e26fa4f0 (Metraipolis archive dc_3d46e26fa4f0, sha256 2a17668c71f0f663dbccb5905ced2547af4b6d82d7c0a292810c6c73c55482f0)
BibTeX
@misc{dc3d46e26fa4f0,
  title = {Evidence lower bound — Wikipedia (en)},
  howpublished = {Wikipedia (en)},
  url = {https://en.wikipedia.org/wiki/Evidence_lower_bound},
  note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_3d46e26fa4f0; sha256 2a17668c71f0f663dbccb5905ced2547af4b6d82d7c0a292810c6c73c55482f0},
  year = {2026}
}

Archived text

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

In variational Bayesian methods, the evidence lower bound (often abbreviated ELBO, also sometimes called the variational lower bound or negative variational free energy) is a useful lower bound on the log-likelihood of some observed data. The ELBO is useful because it provides a guarantee on the worst-case for the log-likelihood of some distribution (e.g. p ( X ) {\displaystyle p(X)} ) which models a set of data. The actual log-likelihood may be higher (indicating an even better fit to the distribution) because the ELBO includes a Kullback-Leibler divergence (KL divergence) term which decreases the ELBO due to an internal part of the model being inaccurate despite good fit of the model overall. Thus improving the ELBO score indicates either improving the likelihood of the model p ( X ) {\displaystyle p(X)} or the fit of a component internal to the model, or both, and the ELBO score makes a good loss function, e.g., for training a deep neural network to improve both the model overall and the internal component. (The internal component is q ϕ ( ⋅ | x ) {\displaystyle q_{\phi }(\cdot |x)} , defined in detail later in this article.)

Tema degli esploratori: statistica e scienza dei dati (deposito sistematico; ricerca «Bayesian statistics»).
Fonte: Wikipedia in inglese, voce «Evidence lower bound» — https://en.wikipedia.org/wiki/Evidence_lower_bound
Wikidata Q55643021 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q55643021
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Evidence_lower_bound?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 1376469012, consultata il 2026-10-07T19:51:23.764Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: 5e8ef35fb469d01f51e6f12794e6050cfbfb5b11fca1c704d837d4a1a1ce38f2