Research map / Multi-agent systems and games / Games and equilibria
Network Effects in Performative Prediction Games
Xiaolu Wang, Chung-Yiu Yau, Hoi To Wai
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 |
|---|---|---|---|
| Increase agent cooperation strength rho (graph regularization) in the MSE Multi-PP game (ablation) | RRM dynamics stability on Multi-PP mean estimation game with asymmetric agent network · Mean estimation (MSE) game, GA and GP as complete/star graphs | RRM convergence condition (spectral radius, Eq. 20) | Mixed |
| Increase population sensitivity eps (distribution shift to model) in the MSE Multi-PP game (ablation) | PSE/RRM stability of Multi-PP mean estimation game · Mean estimation (MSE) game, GA and GP as complete/star graphs | RRM convergence condition (spectral radius, Eq. 20) | Hurt |
| Add graph regularization (rho=1) vs none in multi-agent logistic regression under large negative-sample distribution shift (ablation) | SG-GD on Multi-PP logistic regression (synthetic) · Synthetic logistic regression, GA complete, GP star | test accuracy | Hurt |
| Increase graph regularization rho from 0 to 0.1 under strong performative shift (ablation) | SG-GD on Multi-PP logistic regression (Kaggle Give Me Some Credit) · Kaggle Give Me Some Credit, GA complete, GP star | test accuracy | Hurt |
| Use a sparser/more localized population network (smaller ||P||_inf) instead of dense one | Sufficient condition for PSE existence (Theorem 3.3) · Theoretical analysis | sensitivity threshold for PSE existence | Improved |
Closest papers by meaning
- Multiplayer Performative Prediction: Learning in Decision-Dependent Games (JMLR 2023 · similarity 0.91)
- Decentralized Noncooperative Games with Coupled Decision-Dependent Distributions (NeurIPS 2024 · similarity 0.90)
- Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos (AAAI 2024 · similarity 0.88)
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.86)
- Impact of Decentralized Learning on Player Utilities in Stackelberg Games (ICML 2024 · similarity 0.85)
- Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD (NeurIPS 2024 · 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.
