Research map / Bandits and online learning / Online convex optimization and games
Online Learning for Load Balancing of Unknown Monotone Resource Allocation Games
Ilai Bistritz, Nicholas Bambos
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Adding online pricing-coefficient adjustment (manager updates alpha using total load feedback) versus uncontrolled NE | Power control game · Power control (N=300, K=3) | total throughput: 1184.9 vs 1027.8 at t=750 | Improved |
| Adding online pricing-coefficient adjustment versus uncontrolled NE | Demand-side management game · DSM (N=1000, K=24) | social welfare: 744.7 vs 208.9 at t=100 | Improved |
| Adding online pricing-coefficient adjustment versus the Grammatico (2017) controller | Aggregative game with 2 resources · Comparison with Grammatico 2017 (N=1000, K=2) | convergence time and social welfare | No clear effect |
| Adding the manager's pricing update (vs. Grammatico 2017) in terms of load overshoot | Aggregative game with 2 resources · Comparison with Grammatico 2017 (N=1000, K=2) | total load overshoot | Improved |
Closest papers by meaning
- Towards convergence to Nash equilibria in two-team zero-sum games (ICLR 2023 · similarity 0.88)
- Learning-Augmented Coordination Mechanisms (NeurIPS 2026 · similarity 0.87)
- Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms (NeurIPS 2024 · similarity 0.86)
- Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games (ICML 2025 · similarity 0.86)
- Accelerated Regularized Learning in Finite N-Person Games (NeurIPS 2024 · similarity 0.86)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.85)
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.
