Metraipolis › archive › dc_e04746dc6094
Information projection — Wikipedia (en)
- Source
- Wikipedia (en)
- Original
- https://en.wikipedia.org/wiki/Information_projection
- License (as archived)
- CC-BY-SA-4.0
- Archived
- 2026-10-07T16:39:12.810Z
- SHA-256 of the archived text
0c834992b1ea2f86ba041803fbba3d5df110ca4be4d8def36a73aee1db8d15f4- Stable URL of this page
https://metraipolis.com/documento/dc_e04746dc6094
How to cite
Information projection — Wikipedia (en) — Wikipedia (en), https://en.wikipedia.org/wiki/Information_projection (CC-BY-SA-4.0); archived copy: https://metraipolis.com/documento/dc_e04746dc6094 (Metraipolis archive dc_e04746dc6094, sha256 0c834992b1ea2f86ba041803fbba3d5df110ca4be4d8def36a73aee1db8d15f4)
BibTeX
@misc{dce04746dc6094,
title = {Information projection — Wikipedia (en)},
howpublished = {Wikipedia (en)},
url = {https://en.wikipedia.org/wiki/Information_projection},
note = {License CC-BY-SA-4.0; archived copy https://metraipolis.com/documento/dc_e04746dc6094; sha256 0c834992b1ea2f86ba041803fbba3d5df110ca4be4d8def36a73aee1db8d15f4},
year = {2026}
}Archived text
Reproduced under CC-BY-SA-4.0. Attribution: Wikipedia (en), https://en.wikipedia.org/wiki/Information_projection. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In information theory, the information projection or I-projection of a probability distribution q onto a set of distributions P is p ∗ = arg min p ∈ P D K L ( p | | q ) {\displaystyle p^{*}={\underset {p\in P}{\arg \min }}\operatorname {D} _{\mathrm {KL} }(p||q)} . where D K L {\displaystyle D_{\mathrm {KL} }} is the Kullback–Leibler divergence from q to p. Viewing the Kullback–Leibler divergence as a measure of distance, the I-projection p ∗ {\displaystyle p^{*}} is the "closest" distribution to q of all the distributions in P. The I-projection is useful in setting up information geometry, notably because of the following inequality, valid when P is convex: D K L ( p | | q ) ≥ D K L ( p | | p ∗ ) + D K L ( p ∗ | | q ) {\displaystyle \operatorname {D} _{\mathrm {KL} }(p||q)\geq \operatorname {D} _{\mathrm {KL} }(p||p^{*})+\operatorname {D} _{\mathrm {KL} }(p^{*}||q)} . This inequality can be interpreted as an information-geometric version of Pythagoras' triangle-inequality theorem, where KL divergence is viewed as squared distance in a Euclidean space. It is worthwhile to note that since D K L ( p | | q ) ≥ 0 {\displaystyle \operatorname {D} _{\mathrm {KL} }(p||q)\geq 0} and continuous in p, if P is closed and non-empty, then there exists at least one minimizer to the optimization problem framed above. Furthermore, if P is convex, then the optimum distribution is unique. The reverse I-projection also known as moment projection or M-projection is p ∗ = arg min p ∈ P D K L ( q | | p ) {\displaystyle p^{*}={\underset {p\in P}{\arg \min }}\operatorname {D} _{\mathrm {KL} }(q||p)} . Since the KL divergence is not symmetric in its arguments, the I-projection and the M-projection will exhibit different behavior. For I-projection, p ( x ) {\displaystyle p(x)} will typically under-estimate the support of q ( x ) {\displaystyle q(x)} and will lock onto one of its modes. This is due to p ( x ) = 0 {\displaystyle p(x)=0} , whenever q ( x ) = 0 {\displaystyle q(x)=0} to make sure KL divergence stays finite. For M-projection, p ( x ) {\displaystyle p(x)} will typically over-estimate the support of q ( x ) {\displaystyle q(x)} . This is due to p ( x ) > 0 {\displaystyle p(x)>0} whenever q ( x ) > 0 {\displaystyle q(x)>0} to make sure KL divergence stays finite. The reverse I-projection plays a fundamental role in the construction of optimal e-variables. The concept of information projection can be extended to arbitrary f-divergences and other divergences.
Tema degli esploratori: matematica e informatica teorica (deposito sistematico; ricerca «information theory»).
Fonte: Wikipedia in inglese, voce «Information projection» — https://en.wikipedia.org/wiki/Information_projection
Wikidata Q6031173 (dati Wikidata in CC0 1.0) — https://www.wikidata.org/wiki/Q6031173
Autori: i contributori di Wikipedia (cronologia: https://en.wikipedia.org/wiki/Information_projection?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 1374935631, consultata il 2026-10-07T16:07:43.969Z tramite l'API ufficiale di Wikipedia. Impronta SHA-256 dell'estratto: d1e3450bc6ca0cd5a6427ba60c819422f03edf70612c52dd68cb395e8221f8bb