Formal verification of higher-order probabilistic programs: reasoning about approximation, convergence, Bayesian inference, and optimization

@article{Sato2019FormalVO,
  title={Formal verification of higher-order probabilistic programs: reasoning about approximation, convergence, Bayesian inference, and optimization},
  author={T. Sato and Alejandro Aguirre and G. Barthe and Marco Gaboardi and Deepak Garg and Justin Hsu},
  journal={Proceedings of the ACM on Programming Languages},
  year={2019},
  volume={3},
  pages={1 - 30}
}
Probabilistic programming provides a convenient lingua franca for writing succinct and rigorous descriptions of probabilistic models and inference tasks. Several probabilistic programming languages, including Anglican, Church or Hakaru, derive their expressiveness from a powerful combination of continuous distributions, conditioning, and higher-order functions. Although very important for practical applications, these features raise fundamental challenges for program semantics and verification… Expand
14 Citations
A relational logic for higher-order programs
  • 11
  • PDF
Probabilistic programming semantics for name generation
  • PDF
The next 700 relational program logics
  • 9
  • PDF
Programming and reasoning with partial observability
  • PDF
On algebraic abstractions for concurrent separation logics
  • PDF
Symbolic Disintegration with a Variety of Base Measures
  • 6
  • PDF
A language for probabilistically oblivious computation
  • 10
  • PDF
miniKanren as a Tool for Symbolic Computation in Python
  • PDF
...
1
2
...

References

SHOWING 1-7 OF 7 REFERENCES
Denotational validation of higher-order Bayesian inference
  • 34
  • Highly Influential
  • PDF
Proofs of randomized algorithms in Coq
  • 124
  • Highly Influential
  • PDF
Probabilistic coherence spaces are fully abstract for probabilistic PCF
  • 66
  • Highly Influential
  • PDF
Probabilistic Inference by Program Transformation in Hakaru (System Description)
  • 69
  • Highly Influential
  • PDF
Anonymity, information, and machine-assisted proof
  • 26
  • Highly Influential
  • PDF
Measure Transformer Semantics for Bayesian Machine Learning
  • 57
  • Highly Influential
  • PDF
A Relational Logic for Higherorder Programs
  • Proc. ACM Program. Lang. 1, ICFP, Article 21 (Aug. 2017), 29 pages. https://doi.org/10.1145/3110265
  • 2017