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

Efficient infinite-dimensional optimization over measures

Project description

New tools to improve sampling and handle uncertainty in models

Sampling from complex probability distributions is essential in fields including machine learning, where it helps model uncertainty or generate new data, such as images or text. However, current methods struggle with complex spaces, are difficult to evaluate, are computationally inefficient and are limited to simpler settings (Euclidean spaces). The ERC-funded OptInfinite project will create a unified framework for efficient sampling in general, even infinite dimensional spaces. By using tools from optimal transport and information geometry, researchers will develop new optimisation methods. The outcome will be a powerful toolset for solving advanced optimisation problems and improving sampling techniques.

Objective

Optimization over probability measures has become a powerful approach for solving complex problems
that involve probabilistic modeling. Advanced by the PI and collaborators, it extends finite-dimensional
optimization to the infinite-dimensional space of probability measures. This framework provides a princi-
pled way to address in particular the task of sampling, that refers to the process of drawing samples from
a complex probability distribution, either to approximate it or generate new data. In Bayesian machine
learning for instance, we can model uncertainty of the predictions by sampling a model’s parameters.
Similarly, in generative modeling, sampling is crucial for producing new data such as images or text.
Existing methods struggle with complex measures, are difficult to evaluate, and are limited to Euclidean
spaces, making them unsuitable for infinite-dimensional ones like functions or operators. Also, their lack
of computational efficiency limits their use in sequential sampling tasks. My goal is to create a unified
framework to design and evaluate efficient methods for sampling measures over general spaces.
Central to my approach is the use of tools from optimal transport and information geometry, which will
help compare measures and design optimization dynamics. OptInfinite will advance optimization over
measures by addressing two key challenges: 1) developing optimization objectives and geometries suited to
the space of measures over general (possibly-infinite-dimensional) spaces to design tractable schemes and
metrics, and 2) learning to solve advanced optimization problems, such as sequences of optimization tasks.
This framework will yield novel sampling methods, whose efficiency can be evaluated using optimization
tools. It will also enable to compare measures and reveal where and how they are different. Ultimately,
our work will provide a clear methodology and toolset applicable across multiple domains.

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-STG

See all projects funded under this call

Host institution

GROUPE DES ECOLES NATIONALES D ECONOMIE ET STATISTIQUE
Net EU contribution
€ 1 499 632,00
Address
5 AVENUE HENRY LE CHATELIER
91120 Palaiseau
France
Region
Ile-de-France Ile-de-France Essonne
Activity type
Higher or Secondary Education Establishments
Links
Total cost
€ 1 499 632,50

Beneficiaries (1)