A categorical approach to quantum probabilistic inference

Project funded by Fundação para a Ciência e a Tecnologia, I.P. (FCT), grant 2023.02568.BD. Runs 2023-10-01 to 2027-09-30. Source: OpenAIRE Graph, from the funder's project data (collected by OpenAIRE on 2025-07-19); national funding data, not CORDIS. Abstract given by the source: The quantum computing age is upon us, carrying the promise of increased computational power. The use of quantum systems as information carriers allows for processing information according to the intuition-defying, nonclassical laws of quantum mechanics. This opens new possibilities, with envisaged applications including machine learning and simulation of quantum physical systems. In this project, I will develop mathematical foundations for quantum version(s) of Bayesian inference, generalising a key method of probabilistic reasoning that underpins model-based artificial intelligence. I will adopt a category-theoretic methodology along the lines of Markov categories, aiming for a compositional, synthetic formulation of quantum probability that unifies different instances and illuminates the comparison against the classical theory. This aims to build a framework that not only elucidates the fundamental principles of quantum probability, but also paves the way towards quantum analogues of probabilistic programming languages, which would automate (quantum) Bayesian inference for model-based quantum machine learning.

Original source.

Source: OpenAIRE Graph: projects of national funders, OpenAIRE, from the project data of Fundação para a Ciência e a Tecnologia, I.P. (FCT). Retrieved 2026-10-28. Licence: Creative Commons Attribution 4.0 (OpenAIRE Graph). Selected metadata, adapted presentation; the publisher's record is authoritative. No endorsement by the source is implied. Licence: Creative Commons Attribution 4.0 (CC BY 4.0).

AI-assisted summary: The project "A categorical approach to quantum probabilistic inference" is funded by FCT with grant 2023.02568.BD, running from 2023-10-01 to 2027-09-30. It aims to develop mathematical foundations for quantum Bayesian inference using category-theoretic methods. Suggested technology pillar: computing. Generated by AI from the public source text; it may contain errors and the original source is authoritative.