Causal Strategic Linear Regression
Authors: Yonadav Shavit, Benjamin Edelman, Brian Axelrod
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | As our main contribution, we provide efficient algorithms for learning decision rules that optimize three distinct decision-maker objectives in a realizable linear setting: accurately predicting agents post-gaming outcomes (prediction risk minimization), incentivizing agents to improve these outcomes (agent outcome maximization), and estimating the coefficients of the true underlying model (parameter estimation). Our algorithms circumvent a hardness result of Miller et al. (2020) by allowing the decision maker to test a sequence of decision rules and observe agents responses, in effect performing causal interventions through the decision rules. |
| Researcher Affiliation | Academia | 1Harvard School of Engineering and Applied Sciences, Cambridge, MA, USA 2Stanford Computer Science Department, Palo Alto, CA, USA. Correspondence to: Yonadav Shavit <yonadav@g.harvard.edu>. |
| Pseudocode | Yes | Algorithm 1 Agent Outcome Maximization |
| Open Source Code | No | The paper does not contain any statement about releasing open-source code or provide links to a code repository. |
| Open Datasets | No | The paper is theoretical and describes algorithms with respect to abstract distributions ('P (Rd )') and samples ('{x P}n'), but does not specify any concrete dataset names or provide information about their public availability for training purposes. |
| Dataset Splits | No | The paper does not specify dataset splits (e.g., training, validation, test percentages or counts) as it focuses on theoretical algorithms rather than empirical evaluations on concrete datasets. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU models, CPU types, or memory specifications used for running experiments. |
| Software Dependencies | No | The paper does not provide specific software dependency details, such as library names with version numbers, required to replicate any experiments. |
| Experiment Setup | No | The paper does not include specific experimental setup details such as hyperparameter values, optimizer settings, or other training configurations, as it presents theoretical algorithms rather than empirical studies. |