About: Stochastic gradient Langevin dynamics

Facets (new session)
Description
Metadata
Settings
- Rule:
- Inverse Functional Properties:
- "Same As":

About: Stochastic gradient Langevin dynamics Goto Sponge NotDistinct Permalink

An Entity of Type : owl:Thing, within Data Space : dbpedia.org associated with source document(s)
QRcode icon

http://dbpedia.org/describe/?url=http%3A%2F%2Fdbpedia.org%2Fresource%2FStochastic_gradient_Langevin_dynamics&graph=http%3A%2F%2Fdbpedia.org&graph=http%3A%2F%2Fdbpedia.org

Stochastic gradient Langevin dynamics (SGLD) is an optimization and sampling technique composed of characteristics from Stochastic gradient descent, a Robbins–Monro optimization algorithm, and Langevin dynamics, a mathematical extension of molecular dynamics models. Like stochastic gradient descent, SGLD is an iterative optimization algorithm which uses minibatching to create a stochastic gradient estimator, as used in SGD to optimize a differentiable objective function. Unlike traditional SGD, SGLD can be used for Bayesian learning as a sampling method. SGLD may be viewed as Langevin dynamics applied to posterior distributions, but the key difference is that the likelihood gradient terms are minibatched, like in SGD. SGLD, like Langevin dynamics, produces samples from a posterior distribu

Attributes	Values
rdfs:label	Stochastic gradient Langevin dynamics (en)
rdfs:comment	Stochastic gradient Langevin dynamics (SGLD) is an optimization and sampling technique composed of characteristics from Stochastic gradient descent, a Robbins–Monro optimization algorithm, and Langevin dynamics, a mathematical extension of molecular dynamics models. Like stochastic gradient descent, SGLD is an iterative optimization algorithm which uses minibatching to create a stochastic gradient estimator, as used in SGD to optimize a differentiable objective function. Unlike traditional SGD, SGLD can be used for Bayesian learning as a sampling method. SGLD may be viewed as Langevin dynamics applied to posterior distributions, but the key difference is that the likelihood gradient terms are minibatched, like in SGD. SGLD, like Langevin dynamics, produces samples from a posterior distribu (en)
foaf:depiction
dcterms:subject	Computational statistics Optimization algorithms and methods Stochastic optimization Gradient methods
Wikipage page ID	58878004 (xsd:integer)
Wikipage revision ID	1107781335 (xsd:integer)
Link from a Wikipage to another Wikipage	Bayesian inference Metropolis–Hastings algorithm Computational statistics Deep learning Convex set Critical point (mathematics) Mathematical optimization Gradient descent Condition number Objective function Hamiltonian Monte Carlo Optimization algorithms and methods Langevin dynamics Lattice field theory Molecular dynamics Stochastic gradient descent Stochastic optimization Artificial neural network Gradient methods Differentiable function Total variation Robbins–Monro algorithm
sameAs	Stochastic gradient Langevin dynamics Stochastic gradient Langevin dynamics
dbp:wikiPageUsesTemplate	dbt:Citation_needed dbt:Orphan
thumbnail	wiki-commons:Special:FilePath/Non-Convex_Objective_Function.gif?width=300
has abstract	Stochastic gradient Langevin dynamics (SGLD) is an optimization and sampling technique composed of characteristics from Stochastic gradient descent, a Robbins–Monro optimization algorithm, and Langevin dynamics, a mathematical extension of molecular dynamics models. Like stochastic gradient descent, SGLD is an iterative optimization algorithm which uses minibatching to create a stochastic gradient estimator, as used in SGD to optimize a differentiable objective function. Unlike traditional SGD, SGLD can be used for Bayesian learning as a sampling method. SGLD may be viewed as Langevin dynamics applied to posterior distributions, but the key difference is that the likelihood gradient terms are minibatched, like in SGD. SGLD, like Langevin dynamics, produces samples from a posterior distribution of parameters based on available data. First described by Welling and Teh in 2011, the method has applications in many contexts which require optimization, and is most notably applied in machine learning problems. (en)
prov:wasDerivedFrom	wikipedia-en:Stochastic_gradient_Langevin_dynamics?oldid=1107781335&ns=0
page length (characters) of wiki page	9230 (xsd:nonNegativeInteger)
foaf:isPrimaryTopicOf	wikipedia-en:Stochastic_gradient_Langevin_dynamics
is Link from a Wikipage to another Wikipage of	Stochastic Gradient Langevin Dynamics
is Wikipage redirect of	Stochastic Gradient Langevin Dynamics
is foaf:primaryTopic of	wikipedia-en:Stochastic_gradient_Langevin_dynamics

Faceted Search & Find service v1.17_git139 as of Feb 29 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 08.03.3330 as of Mar 19 2024, on Linux (x86_64-generic-linux-glibc212), Single-Server Edition (61 GB total memory, 42 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software