Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Fair Classification with Adversarial Perturbations
Authors: L. Elisa Celis, Anay Mehrotra, Nisheeth Vishnoi
NeurIPS 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirically, we evaluate the classifiers produced by our framework for statistical rate on real-world and synthetic datasets for a family of adversaries. |
| Researcher Affiliation | Academia | L. Elisa Celis Yale University Anay Mehrotra Yale University Nisheeth K. Vishnoi Yale University |
| Pseudocode | No | The paper presents mathematical programs (Err Tolerant and Err Tolerant+) but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-source code of the described methodology. |
| Open Datasets | Yes | We implement our framework for logistic loss function with linear classifiers and evaluate its performance on COMPAS [3], Adult [23], and a synthetic dataset (Section 5). |
| Dataset Splits | Yes | We use a randomly generated 70-30 train (S) test (T) split of the data, and generate the perturbed data b S from S for a (known) perturbation rate η. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory specifications) used for running experiments. |
| Software Dependencies | Yes | In our simulations, we use the standard solver SLSQP in Sci Py [57] to heuristically find f ET; see Supplementary Material E.1. |
| Experiment Setup | Yes | We implement our framework for logistic loss function with linear classifiers and evaluate its performance on real world and synthetic data... We use a randomly generated 70-30 train (S) test (T) split of the data, and generate the perturbed data b S from S for a (known) perturbation rate η... We take gender (coded as binary) as the protected attribute, and set the fairness constraint on the statistical rate to be τ = 0.9 for Err-Tol and all baselines. |