On preserving non-discrimination when combining expert advice

Authors: Avrim Blum, Suriya Gunasekar, Thodoris Lykouris, Nati Srebro

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our impossibility results for equalized odds. Surprisingly, we show that for a prevalent notion of non-discrimination, equalized odds, it is impossible to preserve non-discrimination while also competing comparably to the best predictor in hindsight (no-regret property). Our results for equalized error rates. The strong impossibility results with respect to equalized odds invite the natural question of whether there exists some alternative fairness notion that, given access to non-discriminatory predictors, achieves efficiency while preserving non-discrimination. We answer the above positively by suggesting the notion of equalized error rates...
Researcher Affiliation Academia Avrim Blum TTI-Chicago avrim@ttic.edu Suriya Gunasekar TTI-Chicago suriya@ttic.edu Thodoris Lykouris Cornell University teddlyk@cs.cornell.edu Nathan Srebro TTI-Chicago nati@ttic.edu
Pseudocode No The paper describes algorithms like 'multiplicative weights' but does not provide structured pseudocode or algorithm blocks.
Open Source Code No The paper does not mention providing open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not involve the use of datasets for training or evaluation.
Dataset Splits No The paper is theoretical and does not involve empirical evaluation with dataset splits (training, validation, test).
Hardware Specification No The paper is theoretical and does not describe any experimental setup or hardware used.
Software Dependencies No The paper is theoretical and does not describe software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with specific hyperparameters or training configurations.