Polynomial Stein discrepancy provides a moment-detecting goodness-of-fit test for Bayesian samples that is cheaper than kernel Stein discrepancy and proven to detect first-r moment differences for Gaussian targets.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2024 2verdicts
UNVERDICTED 2representative citing papers
Bernoulli factory MCMC is adapted to enable exact sampling from targets using proposals with intractable normalizing constants, shown via three examples.
citing papers explorer
-
The Polynomial Stein Discrepancy for Assessing Moment Convergence
Polynomial Stein discrepancy provides a moment-detecting goodness-of-fit test for Bayesian samples that is cheaper than kernel Stein discrepancy and proven to detect first-r moment differences for Gaussian targets.
-
Exact MCMC for Intractable Proposals
Bernoulli factory MCMC is adapted to enable exact sampling from targets using proposals with intractable normalizing constants, shown via three examples.