Neural networks serve as supermartingale certificates inside a counterexample-guided loop that trains on samples and verifies with SMT to produce tight probability bounds for stochastic reachability.
Lexicographic ranking supermartingales: an efficient approach to termination of probabilistic programs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LO 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Quantitative Verification with Neural Networks
Neural networks serve as supermartingale certificates inside a counterexample-guided loop that trains on samples and verifies with SMT to produce tight probability bounds for stochastic reachability.