Meritocratic Fairness for Infinite and Contextual Bandits

By Matthew Joseph, Michael Kearns, Jamie H. Morgenstern, Seth Neel, Aaron Roth. 2018

49 citations recorded by the source corpus.

We study fairness in linear bandit problems. Starting from the notion of meritocratic fairness introduced in~\citeJKMR16, we carry out a more refined analysis of a more general problem, achieving better performance guarantees with fewer modelling assumptions on the number and structure of available choices as well as the number selected. We also analyze the previously-unstudied question of fairness in infinite linear bandit problems, obtaining instance-dependent regret upper bounds as well as lower bounds demonstrating that this instance-dependence is necessary. The result is a framework for meritocratic fairness in an online linear setting that is substantially more powerful, general, and realistic than the current state of the art.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

Beyond Individual and Group Fairness (2020, background): “…problem of fair selection [Kearns et al., 2017, Kleinberg and Raghavan, 2018], online learning and multi-armed bandit problems [Liu et al., 2017, Joseph et al., 2018], in particular stochastic and contextual bandits [Joseph et al., 2016, Gillen et al., 2018, Gupta and Kamble, 2019] and…”
Fairness in Machine Learning: A Survey (2020, unknown): “The main notions of fairness applied in the application of bandits are mer-itocratic fairness [127, 156, 157] (group agnostic), subjective fairness [201] (emphasizes fairness in each time period t ), and counterfactual fairness (e.g., Reference [146]).”
Explainable AI: A Review of Machine Learning Interpretability Methods (2020, background): “[91] performed a more comprehensive analysis on the broader issue of realising superior guarantees in terms of performance, while relaxing the model assumptions.”
Equal Opportunity in Online Classification with Partial Feedback (2019, methodology): “Second, fair online classiﬁcation and regression in the contextual bandit setting [20, 21, 25].”
Average Individual Fairness: Algorithms, Generalization and Experiments (2019, background): “For example, the constraint imposed by Joseph et al. (2016, 2018) in online classiﬁcation problems implies that the false positive rate must be equalized across all pairs of individuals who (truly) have negative labels.”