ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference.
Nikita DurasovNik DorndorfPascal FuaPublished in: CoRR (2022)
Keyphrases
- reasoning under uncertainty
- inference process
- gibbs sampler
- estimation process
- markov chain monte carlo
- importance sampling
- random sampling
- post processing
- probabilistic inference
- estimation accuracy
- estimation error
- markov chain
- bayesian networks
- bayesian inference
- data sets
- accurate estimation
- stochastic simulation
- statistical inference
- inherent uncertainty
- sampling algorithm
- decision theoretic
- iris recognition
- estimation algorithm
- preprocessing step
- density estimation
- parameter estimation
- probabilistic model