Better Languages for Statistics: foundations for non-parametric probabilistic programming

Informazioni relative al progetto

BLaSt

ID dell’accordo di sovvenzione: 864202

DOI

10.3030/864202

Data della firma CE 26 Febbraio 2020

Data di avvio 1 Ottobre 2020

Data di completamento 30 Settembre 2026

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 1 931 178,00

Contributo UE

€ 1 931 178,00

Coordinato da

THE CHANCELLOR, MASTERS AND SCHOLARS OF THE UNIVERSITY OF OXFORD
United Kingdom

Periodic Reporting for period 2 - BLaSt (Better Languages for Statistics: foundations for non-parametric probabilistic programming)

Periodo di rendicontazione: 2022-04-01 al 2023-09-30

Sintesi del contesto e degli obiettivi generali del progetto

Probabilistic programming is a powerful method for Bayesian statistical modelling, particularly where the sample space is complex or unbounded (non-parametric). This is because the statistical model can be described clearly in a way that is precise but separate from inference algorithms. It accommodates complex models in such a way that outcomes are still explainable.

The objective of the proposed research is to develop a semantic foundation for probabilistic programming that properly explains the non-parametric aspects, particularly the symmetries that arise there. There are three ultimate goals:
■ to propose new probabilistic programming languages: better languages for statistics;
■ to devise new general inference methods for probabilistic programs;
■ to build new foundations for probability.

Lavoro eseguito dall’inizio del progetto fino alla fine del periodo coperto dalla relazione e principali risultati finora ottenuti

The work so far has proposed new semantic foundations for programming languages and probabilistic programs, based on categories of concrete sheaves, monads, and Markov categories.

New results in probability theory have also been achieved: new theorems about hierarchical exchangeability, and new treatments of the quantum analogue of de Finetti's theorem.

We have developed new foundations for gradient methods in probabilistic programming.

We have also developed a new programming library for probabilistic programming, based on the techniques developed.

Progressi oltre lo stato dell’arte e potenziale impatto previsto (incluso l’impatto socioeconomico e le implicazioni sociali più ampie del progetto fino ad ora)

For the remainder of the project we will derive new methods in programming languages so as to advance the state of the art in statistics and probability theory.

We hope to prove a conjecture precisely relating programming libraries to "exchangeable process" in non-parametric statistics.

We will further develop our probabilistic programming library based on further developments. We hope to extend it with gradient methods for advanced performance.

regression.jpg