atlas

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

Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos

NeurIPS 2017 · Learning theory and algorithms › Submodular and game algorithms · approach: Correlated equilibria in sequential games · 56 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use linear MWU with arbitrary admissible constant learning ratesCongestion games · General congestion gamesconvergence to exact Nash equilibriumHelped
Use linear rather than exponential MWUTwo-agent, two-strategy load balancing with equal edge costs · Equal-cost load balancing gameconvergence behaviorHelped
Use exponential rather than linear MWU with ε=1-e^{-10}Two-agent, two-strategy load balancing with equal edge costs · Equal-cost load balancing gameconvergence behaviorHurt
Use linear rather than exponential MWUTwo-agent, two-strategy load balancing with unequal edge costs · Unequal-cost load balancing gameconvergence behaviorHelped
Use exponential MWU with ε=1-e^{-40}Two-agent, two-strategy load balancing with unequal edge costs · Unequal-cost load balancing gameconvergence behaviorHurt

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