Foundations of Implicitly Constrained Learning: A Functional Framework
One of 10,000+ projects Taiyo tracks in France.
Source: EU Funding & Tenders Portal
Machine learning has thrived by training expressive models on large datasets, but is now shifting toward integrating prior knowledge—like physical laws or structure—into the learning process. Many such problems can be formulated as an implicitly constrained learning (ICL) task, where a prediction model is subject to a partially known constraint whose unknown component is inferred by aligning mode
- Status
- Prospective
- Location
- France
- Updated
- 19 Nov 2026
- Source
- EU Funding & Tenders Portal
ConstructChat
Ask ConstructChat about Foundations of Implicitly Constrained Learning: A Functional Framework
Pick a question to edit it, or write your own.
First answer free · no account
Project Information FAQ
Project Information
Participants
| Not available for this record. |
Status
Original status | forthcoming |
Taiyo status | Prospective |
Taiyo last update | 2026-11-19 |
Contact
| Not available for this record. |
Description
Description | Machine learning has thrived by training expressive models on large datasets, but is now shifting toward integrating prior knowledge—like physical laws or structure—into the learning process. Many such problems can be formulated as an implicitly constrained learning (ICL) task, where a prediction model is subject to a partially known constraint whose unknown component is inferred by aligning model predictions with data. ICL problems arise across domains: enforcing physics in scientific models, planning from a learned world model, or accounting for hidden variables for causal effect estimation. These settings pose major challenges, especially when using expressive over-parameterized models like deep neural networks: (1) the resulting optimization can become ill-defined; (2) current methods (e.g. differential programming, penalization approaches, neural operators) are often unstable, inaccurate, or inefficient; (3) learning theory for ICL is largely under-developed, limiting understanding of generalization and robustness. The ambition of DELPHI is to establish a principled and efficient methodological framework for solving ICL, capable of handling complex implicit constraints—ranging from auxiliary optimality conditions to partial differential equations and dynamical systems. Our approach adopts a functional viewpoint that reframes ICL as a well-defined yet abstract problem, using deep networks only as approximation tools. The functional viewpoint on ICL will drive theoretical, methodological and practical advances in machine learning, and unlock transformative advances in scientific discovery, causal reasoning, and intelligent decision-making. By reconciling the use of expressive neural approximations with implicit constraints, DELPHI will pave the way toward more reliable, efficient, and principled machine learning. |
Location
Country | France |
Source
Source | EU Funding & Tenders Portal |
URL |
More Details
Record type | Project |
Article published date | 2026-11-15 |
Research
Free account
View all details
You are reading the public part. A free account opens the rest:
- Every detail on this project
- News and media coverage
- Technical research
Free account · no card · lands you back on this project
More infrastructure projects in France
- Projet 18e - Porte de Clignancourt
- Projet Broussais
- 250 premiers projets pour entretenir et rénover Paris
- Protocole d'accord RATP/Ville de Paris: création de 2000 logements d'ici 2024
- Chapelle Dubois Condorcet
- Les dix lauréats de l'appel à projets de l'Arc de l'innovation
- Projet 16e - 17e - Porte Maillot
- Landivisiau Power Plant Brittany
