Research map / Multi-agent systems and games / Games and equilibria
Multi-agent Performative Prediction with Greedy Deployment and Consensus Seeking Agents
Qiang LI, 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 |
|---|---|---|---|
| add consensus communication on the ring graph for an agent with epsilon_i = 1.01 (vs agent running greedy deployment alone) (ablation) | DSGD-GD · Gaussian mean estimation, n=25 ring | performative risk | Improved |
| increase average sensitivity epsilon_avg above 1 (1.01, 1.05, 1.1 vs 0.9) | DSGD-GD · Gaussian mean estimation, n=25 ring | consensus error and performative risk: 0.9 -> 1.01 | Hurt |
| use performative-aware greedy deployment (DSGD-GD) instead of non-performative DSGD solution | decentralized logistic regression · Spambase with shifted distributions | test accuracy | Improved |
| increase average sensitivity epsilon_avg from 0.01 to 0.1 to 1 | DSGD-GD · Spambase with shifted distributions | test accuracy: 0.01 -> 0.1 -> 1 | Hurt |
| vary epsilon_avg in {0.01, 0.1, 1} with heterogeneous epsilon_i | DSGD-GD · Spambase, 25 servers on ring | gradient norm and consensus error convergence | No clear effect |
Closest papers by meaning
- Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss (NeurIPS 2024 · similarity 0.86)
- Decentralized Noncooperative Games with Coupled Decision-Dependent Distributions (NeurIPS 2024 · similarity 0.86)
- Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD (NeurIPS 2024 · similarity 0.85)
- Decentralized Monte Carlo Tree Search for Partially Observable Multi-Agent Pathfinding (AAAI 2024 · similarity 0.85)
- Two-timescale Derivative Free Optimization for Performative Prediction with Markovian Data (ICML 2024 · similarity 0.84)
- The Stability of Online Algorithms in Performative Prediction (NeurIPS 2026 · similarity 0.84)
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.
