ELBO
E835245
ELBO (Evidence Lower Bound) is an objective function used in variational inference to approximate complex probability distributions, particularly in variational autoencoders and related Bayesian models.
All labels observed (1)
| Label | Occurrences |
|---|---|
| ELBO canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T10023658 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ELBO Context triple: [Auto-Encoding Variational Bayes, definesAbbreviation, ELBO]
-
A.
ELKB
ELKB is the Evangelical Lutheran regional church body serving the Protestant community in the German state of Bavaria.
-
B.
LLE
LLE is the station code for Loulé railway station in Portugal’s Algarve region.
-
C.
ELP
ELP is the three-letter IATA airport code for El Paso International Airport, a commercial airport serving El Paso, Texas.
-
D.
ELM
ELM is the commonly used abbreviation for the Estonian Literary Museum, a national research and memory institution dedicated to preserving and studying Estonia’s literary and folkloric heritage.
-
E.
ELM
ELM is the three-letter IATA airport code for Elmira/Corning Regional Airport in New York, United States.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: ELBO Target entity description: ELBO (Evidence Lower Bound) is an objective function used in variational inference to approximate complex probability distributions, particularly in variational autoencoders and related Bayesian models.
-
A.
ELKB
ELKB is the Evangelical Lutheran regional church body serving the Protestant community in the German state of Bavaria.
-
B.
LLE
LLE is the station code for Loulé railway station in Portugal’s Algarve region.
-
C.
ELP
ELP is the three-letter IATA airport code for El Paso International Airport, a commercial airport serving El Paso, Texas.
-
D.
ELM
ELM is the commonly used abbreviation for the Estonian Literary Museum, a national research and memory institution dedicated to preserving and studying Estonia’s literary and folkloric heritage.
-
E.
ELM
ELM is the three-letter IATA airport code for Elmira/Corning Regional Airport in New York, United States.
- F. None of above. chosen
Statements (49)
| Predicate | Object |
|---|---|
| instanceOf |
objective function
ⓘ
variational inference concept ⓘ |
| alternativeForm | log p(x) - KL(q(z|x) || p(z|x)) ⓘ |
| bounds | log marginal likelihood from below ⓘ |
| canBe |
decomposed into sum over data points
ⓘ
estimated with Monte Carlo samples ⓘ |
| centralRoleIn | training of variational autoencoders (VAEs) ⓘ |
| definedOver |
latent variables
ⓘ
observed variables ⓘ variational distribution ⓘ |
| dependsOn |
model parameters
ⓘ
variational parameters ⓘ |
| fullName | Evidence Lower Bound ⓘ |
| hasTerm |
reconstruction term
ⓘ
regularization term ⓘ |
| introducedInContextOf | variational methods in Bayesian statistics ⓘ |
| isLowerBoundOn | log p(x) ⓘ |
| mathematicalDomain |
machine learning
ⓘ
probability theory ⓘ |
| maximizationEquivalentTo | minimizing KL divergence between variational posterior and true posterior ⓘ |
| optimizedBy |
reparameterization trick
ⓘ
stochastic gradient descent ⓘ stochastic variational inference ⓘ |
| property |
non-convex in general for deep models
ⓘ
tighter ELBO implies better approximation to true posterior ⓘ |
| regularizationTermOften | KL(q(z|x) || p(z)) ⓘ |
| relatedTo |
Kullback–Leibler divergence
NERFINISHED
ⓘ
log evidence ⓘ marginal likelihood ⓘ negative variational free energy ⓘ variational free energy ⓘ |
| typicalForm | E_q[log p(x,z)] - E_q[log q(z)] ⓘ |
| usedFor |
approximating complex probability distributions
ⓘ
learning generative models ⓘ optimizing variational distributions ⓘ training probabilistic models with latent variables ⓘ |
| usedIn |
Bayesian inference
ⓘ
Bayesian neural networks NERFINISHED ⓘ amortized variational inference ⓘ approximate Bayesian inference ⓘ black-box variational inference ⓘ deep generative models ⓘ latent variable models ⓘ probabilistic programming ⓘ variational autoencoder ⓘ variational inference ⓘ |
| variant |
beta-ELBO
ⓘ
hierarchical ELBO ⓘ importance-weighted ELBO ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: ELBO Description of subject: ELBO (Evidence Lower Bound) is an objective function used in variational inference to approximate complex probability distributions, particularly in variational autoencoders and related Bayesian models.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.