On intelligenCE And Networks

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, incentives) for their participation in data exchanges.

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 Constraints

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

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

The principal investigators (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.