|
gptkbp:instanceOf
|
gptkb:algorithm
|
|
gptkbp:advantage
|
reduces random walk behavior
improves mixing efficiency
|
|
gptkbp:alsoKnownAs
|
gptkb:Hamiltonian_Monte_Carlo
|
|
gptkbp:application
|
Bayesian inference
neural network training
lattice quantum chromodynamics
|
|
gptkbp:basedOn
|
gptkb:Markov_chain_Monte_Carlo
Hamiltonian dynamics
|
|
gptkbp:category
|
gptkb:Monte_Carlo_methods
gptkb:Markov_chain_Monte_Carlo_methods
|
|
gptkbp:component
|
leapfrog integrator
Metropolis acceptance step
|
|
gptkbp:developedBy
|
gptkb:Anthony_D._Kennedy
gptkb:Brian_J._Pendleton
gptkb:Simon_Duane
D. Roweth
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Hybrid Monte Carlo
|
|
gptkbp:publicationYear
|
1987
|
|
gptkbp:publishedIn
|
gptkb:Physics_Letters_B
|
|
gptkbp:purpose
|
sampling from complex probability distributions
|
|
gptkbp:relatedTo
|
gptkb:Gibbs_sampling
gptkb:Metropolis–Hastings_algorithm
|
|
gptkbp:requires
|
gradient of log-probability density
|
|
gptkbp:usedIn
|
gptkb:machine_learning
Bayesian statistics
computational physics
|
|
gptkbp:bfsParent
|
gptkb:Hamiltonian_Monte_Carlo
|
|
gptkbp:bfsLayer
|
6
|