Timezone: »

Probabilistic Programs with Stochastic Conditioning
David Tolpin · Yuan Zhou · Tom Rainforth · Hongseok Yang

Wed Jul 21 05:40 PM -- 05:45 PM (PDT) @ None

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.

Author Information

David Tolpin (Ben-Gurion University of the Negev)


Yuan Zhou (Artificial Intelligence Research Center, DII)
Tom Rainforth (University of Oxford)
Hongseok Yang (KAIST)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors