Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

Algorithmic Uncertainty Quantification for Learning and Decision Making

Project description

Accurately assessing the uncertainty of machine-learning algorithmic outcomes

Modern large-scale machine learning systems underpin societally important applications including generative AI, autonomous vehicles and robotics, finance and fraud detection, healthcare and medical applications. They use distributed computing to process massive data, supporting real-world decisions. Accurate assessment of their inherent uncertainty is crucial to using them safely and appropriately. The ERC-funded AUQuant project aims to develop new statistical methods to rigorously measure the accuracy of machine learning system outputs together with a theory of algorithmic uncertainty quantification. The tools will be applied to a variety of statistical tasks, advancing areas including statistical learning theory and reinforcement learning while supporting the development of future machine-learning systems.

Objective

Assessing the uncertainty of predictions of modern large-scale machine learning systems is crucial for understanding their limitations and the quality of solutions they provide, especially so when these systems are used for making decisions in the real world. Motivated by this need, this project addresses a variety of questions of uncertainty quantification and develops new methods for deriving statistical guarantees on the accuracy of outputs of ML systems. Our methodology is inspired by an emerging line of work we call algorithmic statistics, which uses tools from the theory of algorithms to prove complex statistical statements. We propose to extend these techniques to the more challenging domain of analyzing modern large-scale machine learning systems, and develop a theory of Algorithmic Uncertainty Quantification. Using the newly developed tools, we will address diverse statistical tasks such as bounding the generalization error of machine learning algorithms, estimating the parameters of large nonlinear statistical models, or designing provably efficient algorithms for interactive decision-making problems. The results will significantly advance the state of the art in well-studied areas of research such as statistical learning theory and reinforcement learning, not only by providing new tools for the analysis of existing algorithms and architectures but also by inspiring new principles for the development of the next generation of ML systems.

Fields of science (EuroSciVoc)

Keywords

Programme(s)

Topic(s)

Funding Scheme

HORIZON-ERC - HORIZON ERC Grants

See all projects funded under this funding scheme

Call for proposal

(opens in new window) ERC-2025-COG

See all projects funded under this call

Host institution

UNIVERSIDAD POMPEU FABRA
Net EU contribution
€ 1 999 757,00
Address
PLACA DE LA MERCE, 10-12
08002 Barcelona
Spain
Region
Este Cataluña Barcelona
Activity type
Higher or Secondary Education Establishments
Links
Total cost
€ 1 999 757,00

Beneficiaries (1)