DC Field | Value | Language |
---|---|---|
dc.contributor.author | Tolpin, David | ko |
dc.contributor.author | Zhou, Yuan | ko |
dc.contributor.author | Rainforth, Tom | ko |
dc.contributor.author | 양홍석 | ko |
dc.date.accessioned | 2021-11-09T06:47:17Z | - |
dc.date.available | 2021-11-09T06:47:17Z | - |
dc.date.created | 2021-11-08 | - |
dc.date.created | 2021-11-08 | - |
dc.date.issued | 2021-07-21 | - |
dc.identifier.citation | The 38th International Conference on Machine Learning (ICML 2021), pp.10312 - 10323 | - |
dc.identifier.uri | http://hdl.handle.net/10203/289018 | - |
dc.description.abstract | We tackle the problem of conditioning probabilistic programs on distributions of observable variables. Probabilistic programs are usually conditioned on samples from the joint data distribution, which we refer to as deterministic conditioning. However, in many real-life scenarios, the observations are given as marginal distributions, summary statistics, or samplers. Conventional probabilistic programming systems lack adequate means for modeling and inference in such scenarios. We propose a generalization of deterministic conditioning to stochastic conditioning, that is, conditioning on the marginal distribution of a variable taking a particular form. To this end, we first define the formal notion of stochastic conditioning and discuss its key properties. We then show how to perform inference in the presence of stochastic conditioning. We demonstrate potential usage of stochastic conditioning on several case studies which involve various kinds of stochastic conditioning and are difficult to solve otherwise. Although we present stochastic conditioning in the context of probabilistic programming, our formalization is general and applicable to other settings. | - |
dc.language | English | - |
dc.publisher | ICML Organisation | - |
dc.title | Probabilistic Programs with Stochastic Conditioning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000768182700030 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 10312 | - |
dc.citation.endingpage | 10323 | - |
dc.citation.publicationname | The 38th International Conference on Machine Learning (ICML 2021) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Online | - |
dc.contributor.localauthor | 양홍석 | - |
dc.contributor.nonIdAuthor | Tolpin, David | - |
dc.contributor.nonIdAuthor | Zhou, Yuan | - |
dc.contributor.nonIdAuthor | Rainforth, Tom | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.