Scaling up Bayesian variational inference using distributed computing clusters.
Andrés R. MasegosaAna M. MartínezHelge LangsethThomas D. NielsenAntonio SalmerónDarío Ramos-LópezAnders L. MadsenPublished in: Int. J. Approx. Reason. (2017)
Keyphrases
- distributed computing
- variational inference
- bayesian inference
- posterior distribution
- topic models
- distributed environment
- probabilistic graphical models
- gaussian process
- mixture model
- probabilistic model
- distributed systems
- variational methods
- latent dirichlet allocation
- closed form
- fault tolerance
- mobile agents
- exponential family
- latent variables
- cloud computing
- probability distribution
- hyperparameters
- clustering algorithm
- markov chain monte carlo
- prior information
- bayesian framework
- factor graphs
- virtual machine
- peer to peer
- graphical models
- parameter estimation
- data points
- maximum a posteriori
- maximum likelihood
- exact inference
- bayesian networks
- posterior probability
- particle filter
- load balancing
- approximate inference
- markov networks
- optic flow