Probabilistic Programs as Spreadsheet Queries

Gordon, Andrew D.; Russo, Claudio; Szymczak, Marcin; Borgström, Johannes; Rolland, Nicolas; Graepel, Thore; Tarlow, Daniel

doi:10.1007/978-3-662-46669-8_1

Cited by 3 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We train the classifier by supplying training data and prior distributions, which we choose to be uninformative in order to remove bias by choice of prior information. We expressed our model in Tabular (Gordon et al 2015), a probabilistic programming language embedded in Microsoft Excel. Tabular models compile into Infer.NET (Minka et al 2012) inference code, in which we use the Variational Message Passing inference algorithm (Winn & Bishop 2005) for training and testing.…”

Section: Analysis and Modellingmentioning

confidence: 99%

Monitoring internet trade to inform species conservation actions

Vaglica¹,

Sajeva²,

McGough

et al. 2017

Endang. Species. Res.

View full text Add to dashboard Cite

Specimens, parts and products of threatened species are commonly traded on the internet. This could threaten the survival of some wild populations. We outline 2 methods to monitor internet sales of species to assess potential threats and inform conservation actions. Our first method combines systematic monitoring of online offers of plants for sale with expert consultation. Our second method utilises a computational model, trained to expert-classified records using probabilistic inference, to predict unknown properties of the traded taxa. We used these methods to monitor internet trade in 5 genera of succulent plant species endemic to Madagascar, some of which have recently been listed for trade regulation under the Convention on International Trade in Endangered Species (CITES). This revealed potential threats to wild populations: for instance, almost all species recorded were of high conservation concern, yet most offers for live plants were of apparently wild-collected specimens (85%). Our model predicted with 89% accuracy whether the plants were classified as propagated or wild collected by an expert, although accuracy dropped for data collected in the following summer. Our results highlight potential threats by internet trade to the survival of some CITES and non-CITES listed plant species from Madagascar. These should be addressed by further conservation actions and policy. More generally, our results reveal how standardised internet surveys can provide information on levels of trade in wild-collected threatened species that could impact on natural populations, and can provide data that can be incorporated into models to facilitate future monitoring and enforcement.

show abstract

Section: Analysis and Modellingmentioning

confidence: 99%

Monitoring internet trade to inform species conservation actions

Vaglica¹,

Sajeva²,

McGough

et al. 2017

Endang. Species. Res.

View full text Add to dashboard Cite

show abstract

“…A revised version of the language, described by Gordon et al (2015), added support for user-defined functions and queries, as described earlier in this section. The original type system was replaced by a simpler one, in which types themselves have a similar form to Core Tabular tables.…”

Section: Retrospective and Related Projectsmentioning

confidence: 99%

“…The new type system supports basic dependent types and provides space annotations dividing columns into deterministic, random and query columns. The semantics of the new version of Tabular consists of a reduction system reducing schemas with functions and indexing to the Core form and a semantics of Core Tabular models (omitted in this chapter, see the long version of the aforementioned paper (Gordon et al, 2014a)), defined directly in terms of measure theory. Reduction to Core form is proven type-sound.…”

Section: Retrospective and Related Projectsmentioning

confidence: 99%

“…In the syntax of the new version of Tabular presented in the paper which was the starting point for this work (Gordon et al, 2015), each column only has one name. This causes a problem with alphaconversion: if a column is visible outside the given table, then its name cannot be alpha-convertible, since renaming the column would break references to it from outside the table.…”

Section: Motivation For Double Column Namesmentioning

confidence: 99%

See 1 more Smart Citation

Foundations of Probabilistic Programming

Gibbons¹

2020

View full text Add to dashboard Cite

What does a probabilistic program actually compute? How can one formally reason about such probabilistic programs? This valuable guide covers such elementary questions and more. It provides a state-of-the-art overview of the theoretical underpinnings of modern probabilistic programming and their applications in machine learning, security, and other domains, at a level suitable for graduate students and non-experts in the field. In addition, the book treats the connection between probabilistic programs and mathematical logic, security (what is the probability that software leaks confidential information?), and presents three programming languages for different applications: Excel tables, program testing, and approximate computing. This title is also available as Open Access on Cambridge Core.

show abstract

“…SlicStan uses type inference in an information-flow type system [Abadi et al 1999;Gordon et al 2015;Volpano et al 1996] to automatically rearrange the program into parts roughly corresponding to the blocks-structure of Stan: pre-processing (data), model and post-processing (generated quantities). Originally, this shredding was developed to compile SlicStan to Stan.…”

Section: Slicstan: Extended Syntax and Semanticsmentioning

confidence: 99%

Conditional independence by typing

Gorinova,

Gordon,

Sutton

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

A central goal of probabilistic programming languages (PPLs) is to separate modelling from inference. However, this goal is hard to achieve in practice. Users are often forced to re-write their models in order to improve efficiency of inference or meet restrictions imposed by the PPL. Conditional independence (CI) relationships among parameters are a crucial aspect of probabilistic models that captures a qualitative summary of the specified model and can facilitate more efficient inference.We present an information flow type system for probabilistic programming that captures conditional independence (CI) relationships, and show that, for a well-typed program in our system, the distribution it implements is guaranteed to have certain CI-relationships. Further, by using type inference, we can statically deduce which CI-properties are present in a specified model.As a practical application, we consider the problem of how to perform inference on models with mixed discrete and continuous parameters. Inference on such models is challenging in many existing PPLs, but can be improved through a workaround, where the discrete parameters are used implicitly, at the expense of manual model re-writing. We present a source-to-source semantics-preserving transformation, which uses our CI-type system to automate this workaround by eliminating the discrete parameters from a probabilistic program. The resulting program can be seen as a hybrid inference algorithm on the original program, where continuous parameters can be drawn using efficient gradient-based inference methods, while the discrete parameters are drawn using variable elimination.We implement our CI-type system and its example application in SlicStan: a compositional variant of Stan. 1

show abstract

Probabilistic Programs as Spreadsheet Queries

Cited by 3 publications

References 19 publications

Monitoring internet trade to inform species conservation actions

Monitoring internet trade to inform species conservation actions

Foundations of Probabilistic Programming

Conditional independence by typing

Contact Info

Product

Resources

About