Introduces independent subproblem inference and proves asymptotic convergence guarantees for hybrid MCMC algorithms defined via inference metaprogramming.
An Abstract Monte-Carlo Method for the Analysis of Probabilistic Programs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We introduce a new method, combination of random testing and abstract interpretation, for the analysis of programs featuring both probabilistic and non-probabilistic nondeterminism. After introducing "ordinary" testing, we show how to combine testing and abstract interpretation and give formulas linking the precision of the results to the number of iterations. We then discuss complexity and optimization issues and end with some experimental results.
fields
cs.PL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Compositional Inference Metaprogramming with Convergence Guarantees
Introduces independent subproblem inference and proves asymptotic convergence guarantees for hybrid MCMC algorithms defined via inference metaprogramming.