Gradient estimation of probabilistic programs reduces soundly to probabilistic inference after programmable coupling and factorization, enabling new low-variance estimators that beat baselines.
Luke Ong, and Dominik Wagner
1 Pith paper cite this work, alongside 4 external citations. Polarity classification is still indexing.
1
Pith paper citing it
4
external citations · OpenAlex
fields
cs.PL 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
GradInf: Gradient Estimation as Probabilistic Inference
Gradient estimation of probabilistic programs reduces soundly to probabilistic inference after programmable coupling and factorization, enabling new low-variance estimators that beat baselines.