Laddar...

Neural network gradient Hamiltonian Monte Carlo

Hamiltonian Monte Carlo is a widely used algorithm for sampling from posterior distributions of complex Bayesian models. It can efficiently explore high-dimensional parameter spaces guided by simulated Hamiltonian flows. However, the algorithm requires repeated gradient calculations, and these compu...

Full beskrivning

Sparad:
Bibliografiska uppgifter
I publikationen:Comput Stat
Huvudupphovsmän: Li, Lingge, Holbrook, Andrew, Shahbaba, Babak, Baldi, Pierre
Materialtyp: Artigo
Språk:Inglês
Publicerad: 2019
Ämnen:
Länkar:https://ncbi.nlm.nih.gov/pmc/articles/PMC6833949/
https://ncbi.nlm.nih.gov/pubmed/31695242
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1007/s00180-018-00861-z
Taggar: Lägg till en tagg
Inga taggar, Lägg till första taggen!