Unintended Selection: Persistent Qualification Rate Disparities and Interventions
Authors: Reilly Raab, Yang Liu
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We next simulate the effects of commonly proposed fairness interventions on this dynamical system along with a new feedback control mechanism capable of permanently eliminating group-level qualification rate disparities. We compare interventions by appeal to simulation, choosing a setting that guarantees a single, stable average qualification rate s under group-independent policies (GI) (Fig. 3). |
| Researcher Affiliation | Academia | Reilly Raab Computer Science and Engineering University of California, Santa Cruz Santa Cruz, CA 95064 reilly@ucsc.edu Yang Liu Computer Science and Engineering University of California, Santa Cruz Santa Cruz, CA 95064 yangliu@ucsc.edu |
| Pseudocode | No | The paper describes theoretical models and mathematical formulations but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code, nor does it include links to a code repository or mention code in supplementary materials. |
| Open Datasets | No | The paper presents a theoretical model and conducts simulations based on parameters (e.g., 'q0 and q1 are Gaussians with unit variance and have means 1 and 1, respectively.') rather than using or providing access to a publicly available or open dataset. |
| Dataset Splits | No | The paper describes a simulation study based on mathematical models and parameters, not empirical experiments with datasets that require train/validation/test splits. |
| Hardware Specification | No | The paper describes theoretical modeling and simulations but does not provide any specific details about the hardware used for computations. |
| Software Dependencies | No | The paper focuses on theoretical models and simulations, but it does not specify any software dependencies or version numbers (e.g., programming languages, libraries, or solvers) used for the implementation or experiments. |
| Experiment Setup | Yes | q0 and q1 are Gaussians with unit variance and have means 1 and 1, respectively. Other examples and rendered dynamical variables are provided in Appendix C. For this example, (U0ˆ0 = 0.1; U0ˆ1 = 5.5; U1ˆ0 = 0.5; U1ˆ1 = 1.0; V0ˆ0 = 0.5; V0ˆ1 = 0.5; V1ˆ0 = 0.25; V1ˆ1 = 1.0). |