Gradient estimation of probabilistic programs reduces soundly to probabilistic inference after programmable coupling and factorization, enabling new low-variance estimators that beat baselines.
Title resolution pending
3 Pith papers cite this work, alongside 30 external citations. Polarity classification is still indexing.
3
Pith papers citing it
30
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Develops compositional incrementalization of density functions for probabilistic programs to accelerate Monte Carlo inference algorithms.
Graded coalgebras for graded monads are proposed to capture continuous-time transition systems, with developed theory for terminal coalgebras, branching and trace semantics, and coalgebraic modal logics.
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.
-
Incremental Computation for Efficient Programmable Inference in Probabilistic Programs
Develops compositional incrementalization of density functions for probabilistic programs to accelerate Monte Carlo inference algorithms.
-
Graded Monad Coalgebras for Continuous-Time Transition Systems
Graded coalgebras for graded monads are proposed to capture continuous-time transition systems, with developed theory for terminal coalgebras, branching and trace semantics, and coalgebraic modal logics.