On intelligenCE And Networks

OCEAN aims to develop decentralized machine learning frameworks for incentive-driven agents, enhancing data handling and decision-making in competitive environments while addressing privacy and efficiency issues.

Subsidie
€ 7.762.668
2023

Projectdetails

Introduction

Until recently, most of the major advances in machine learning and decision making have focused on a centralized paradigm in which data are aggregated at a central location to train models and/or decide on actions. This paradigm faces serious flaws in many real-world cases.

Challenges of Centralized Learning

In particular, centralized learning risks exposing user privacy, makes inefficient use of communication resources, creates data processing bottlenecks, and may lead to concentration of economic and political power.

Need for Decentralized Learning

It thus appears most timely to develop the theory and practice of a new form of machine learning that targets heterogeneous, massively decentralized networks, involving self-interested agents who expect to receive value (or rewards, incentive) for their participation in data exchanges.

OCEAN Project Overview

OCEAN will develop statistical and algorithmic foundations for systems involving multiple incentive-driven learning and decision-making agents, including uncertainty quantification at the agent's level.

Market Interaction

OCEAN will study the interaction of learning with market constraints, including:

  1. Scarcity
  2. Fairness

This will connect adaptive microeconomics and market-aware machine learning.

Foundations and Expertise

OCEAN builds on a decade of joint advances in:

  • Stochastic optimization
  • Probabilistic machine learning
  • Statistical inference
  • Bayesian assessment of uncertainty
  • Computation
  • Game theory
  • Information science

PIs have complementary and internationally recognized skills in these domains.

Goals and Impact

OCEAN will shed new light on the value and handling of data in a competitive, potentially antagonistic multi-agent environment. It aims to develop new theories and methods to address these pressing challenges.

Conclusion

OCEAN requires a fundamental departure from standard approaches and leads to major scientific interdisciplinary endeavors that will transform statistical learning in the long term while opening up exciting and novel areas of research.

Financiële details & Tijdlijn

Financiële details

Subsidiebedrag€ 7.762.668
Totale projectbegroting€ 7.762.668

Tijdlijn

Startdatum1-3-2023
Einddatum28-2-2029
Subsidiejaar2023

Partners & Locaties

Projectpartners

  • ECOLE POLYTECHNIQUEpenvoerder
  • UNIVERSITE PARIS DAUPHINE
  • THE REGENTS OF THE UNIVERSITY OF CALIFORNIA
  • GROUPE DES ECOLES NATIONALES D ECONOMIE ET STATISTIQUE
  • UNIVERSITY OF WARWICK
  • UNIVERSITY OF NEWCASTLE UPON TYNE
  • UNIVERSITY OF DURHAM
  • UNIVERSITY OF ESSEX

Land(en)

FranceUnited StatesUnited Kingdom

Vergelijkbare projecten binnen European Research Council

ERC Starting...

Semi-Centralized Platforms for Steering Online Multi-Learner Environments

This project aims to develop semi-centralized platforms that combine decentralized learning flexibility with centralized optimization to enhance efficiency, fairness, and accountability in multi-learner environments.

€ 1.316.544
ERC Starting...

Challenges in Competitive Online Optimisation

This project aims to enhance decision-making under uncertainty by developing new online and learning-augmented algorithms, leveraging recent advancements in algorithm design and machine learning.

€ 1.499.828
ERC Advanced...

Control for Deep and Federated Learning

CoDeFeL aims to enhance machine learning methods through control theory, developing efficient ResNet architectures and federated learning techniques for applications in digital medicine and recommendations.

€ 2.499.224
ERC Starting...

Federated and distributed inference leveraging sensing and communication in the computing continuum

This project aims to develop a framework for federated and distributed inference systems that optimizes sensing data processing across edge and cloud environments, enhancing efficiency, security, and performance.

€ 1.019.000
ERC Consolid...

Reinventing Multiterminal Coding for Intelligent Machines

IONIAN aims to revolutionize cooperative perception in intelligent machines by developing a multiterminal coding paradigm that enhances data compression and communication for safer autonomous navigation.

€ 1.999.403

Vergelijkbare projecten uit andere regelingen

LIFE NGO Ope...

Oceana Europe SGA 2025

Oceana in Europe aims to enhance ocean conservation and sustainable fisheries through science-based campaigns, policy advocacy, and public engagement to address climate change and biodiversity loss.

€ 700.000