Nesting probabilistic programs
We formalize the notion of nesting probabilistic programming queries and investigate the resulting statistical implications. We demonstrate that while query nesting allows the definition of models which could not otherwise be expressed, such as those involving agents reasoning about other agents, ex...
| Main Author: | |
|---|---|
| Format: | Conference item |
| Published: |
Association for Uncertainty in Artificial Intelligence
2018
|
| _version_ | 1797086281826566144 |
|---|---|
| author | Rainforth, T |
| author_facet | Rainforth, T |
| author_sort | Rainforth, T |
| collection | OXFORD |
| description | We formalize the notion of nesting probabilistic programming queries and investigate the resulting statistical implications. We demonstrate that while query nesting allows the definition of models which could not otherwise be expressed, such as those involving agents reasoning about other agents, existing systems take approaches which lead to inconsistent estimates. We show how to correct this by delineating possible ways one might want to nest queries and asserting the respective conditions required for convergence. We further introduce a new online nested Monte Carlo estimator that makes it substantially easier to ensure these conditions are met, thereby providing a simple framework for designing statistically correct inference engines. We prove the correctness of this online estimator and show that, when using the recommended setup, its asymptotic variance is always better than that of the equivalent fixed estimator, while its bias is always within a factor of two. |
| first_indexed | 2024-03-07T02:19:50Z |
| format | Conference item |
| id | oxford-uuid:a3868678-1032-46a3-91a5-ebf686f41863 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T02:19:50Z |
| publishDate | 2018 |
| publisher | Association for Uncertainty in Artificial Intelligence |
| record_format | dspace |
| spelling | oxford-uuid:a3868678-1032-46a3-91a5-ebf686f418632022-03-27T02:27:37ZNesting probabilistic programsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:a3868678-1032-46a3-91a5-ebf686f41863Symplectic Elements at OxfordAssociation for Uncertainty in Artificial Intelligence2018Rainforth, TWe formalize the notion of nesting probabilistic programming queries and investigate the resulting statistical implications. We demonstrate that while query nesting allows the definition of models which could not otherwise be expressed, such as those involving agents reasoning about other agents, existing systems take approaches which lead to inconsistent estimates. We show how to correct this by delineating possible ways one might want to nest queries and asserting the respective conditions required for convergence. We further introduce a new online nested Monte Carlo estimator that makes it substantially easier to ensure these conditions are met, thereby providing a simple framework for designing statistically correct inference engines. We prove the correctness of this online estimator and show that, when using the recommended setup, its asymptotic variance is always better than that of the equivalent fixed estimator, while its bias is always within a factor of two. |
| spellingShingle | Rainforth, T Nesting probabilistic programs |
| title | Nesting probabilistic programs |
| title_full | Nesting probabilistic programs |
| title_fullStr | Nesting probabilistic programs |
| title_full_unstemmed | Nesting probabilistic programs |
| title_short | Nesting probabilistic programs |
| title_sort | nesting probabilistic programs |
| work_keys_str_mv | AT rainfortht nestingprobabilisticprograms |