Research map / Multi-agent systems and games / Games and equilibria
Causal Strategic Linear Regression
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Adaptive/non-adaptive decision-rule interventions: publishing a decision rule per basis vector (Algorithm 1) to estimate the gradient of agent outcomes | Agent outcome maximization in causal strategic linear regression · realizable linear setting with quadratic action cost | agent outcome AO(ω) within ϵ of optimum | Helped |
| Using decision rules as causal interventions to recover the outcome-maximizing rule, circumventing the hardness result of Miller et al. (2020) | Agent outcome maximization · theoretical, realizable linear setting | rounds and samples required | Helped |
| Relaxed convex prediction-risk oracle with fallback to gaming-free risk when the decision rule underestimates gaming effects | Prediction risk minimization · realizable linear setting with quadratic action cost | prediction risk | Helped |
| Publishing an informative decision rule ω (chosen via convex optimization) before running OLS, instead of ungamed OLS | Parameter estimation · fully visible features (V = I) linear setting | convergence rate of parameter estimation | Helped |
| Omitting hidden outcome-affecting features from the decision rule (visible-only rule) | Strategic learning with hidden causal features · car insurance toy example | agent outcomes, prediction risk, parameter estimation (mutual non-satisfiability | Mixed |
| Algorithms trade short-term accuracy for long-term gains by exploring decision rules | Causal strategic learning exploration rounds · discussion | decision-maker accuracy in short term | Hurt |
Closest papers by meaning
- Who’s Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation (NeurIPS 2024 · similarity 0.89)
- Causal Strategic Learning with Competitive Selection (AAAI 2024 · similarity 0.89)
- Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty (NeurIPS 2025 · similarity 0.87)
- Prediction-Intervention Games and Invariant Sets (NeurIPS 2026 · similarity 0.85)
- Should Decision-Makers Reveal Classifiers in Online Strategic Classification? (ICML 2025 · similarity 0.85)
- Understanding Model Selection for Learning in Strategic Environments (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.