Graph reparameterizations for enabling 1000+ Monte Carlo iterations in Bayesian deep neural networks.
Jurijs NazarovsRonak R. MehtaVishnu Suresh LokhandeVikas SinghPublished in: UAI (2021)
Keyphrases
- monte carlo
- neural network
- monte carlo methods
- markov chain
- importance sampling
- monte carlo tree search
- simulation study
- monte carlo simulation
- monte carlo method
- bayesian learning
- bayesian networks
- stochastic approximation
- markov chain monte carlo
- markovian decision
- global illumination
- game tree
- bayesian inference
- particle filter
- adaptive sampling
- temporal difference
- game tree search
- optimal strategy
- confidence intervals
- posterior distribution
- policy evaluation
- maximum likelihood