atlas

Research map / Learning theory and algorithms / Submodular and game algorithms

Learning-Augmented Coordination Mechanisms

NeurIPS 2026 · Learning theory and algorithms › Submodular and game algorithms · approach: Correlated equilibria in sequential games

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies learning-augmented coordination mechanisms for congestion games, using untrusted predictions to improve equilibrium inefficiency (PoA/PoS) bounds.

Problem

Decentralized resource allocation in congestion games is inefficient at equilibrium, measured by Price of Anarchy and Price of Stability; classical worst-case bounds can be poor, motivating use of predictions to improve coordination mechanisms.

Approach

Augments coordination mechanisms for atomic and non-atomic congestion games with learned predictions, aiming to mitigate the worst-case inefficiency of equilibria while retaining robustness to prediction error.

Experimental setup

Metrics: price of anarchy price of stability

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy