Fair Learning in Markovian Environments

By Shahin Jabbari, Matthew Joseph, Michael Kearns, Jamie H. Morgenstern, Aaron Roth. 2016

35 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Fair Inference on Outcomes (2017, background): “…by deﬁning, analyzing, and mitigating harmful effects of algorithmic bias from a variety of perspectives and frameworks (Pedreshi, Ruggieri, and Turini 2008; Feldman et al. 2015; Hardt, Price, and Srebro 2016; Kamiran, Zliobaite, and Calders 2013; Corbe-Davies et al. 2017; Jabbari et al. 2016).”
Runaway Feedback Loops in Predictive Policing (2017, background): “In addition, it relates to the narrower question of defining notions of fairness in sequential learning settings such as the setting of bandits (regular, contextual and linear) and Markov decision processes[6, 5, 3, 4].”
Empirical Risk Minimization under Fairness Constraints (2018, background): “mpirically effective and performs favorably against state-of-the-art approaches. 1 Introduction In recent years there has been a lot of interest on algorithmic fairness in machine learning see, e.g., [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13] and references therein. The central question is how to e”
Calibrated Fairness in Bandits (2017, neutral): “[10] also extend the notion of weakly meritocratic fairness to Markovian environments, whereby fairness requires the algorithm to be more likely to play actions that have a higher utility under the optimal policy.”
Meritocratic Fairness for Cross-Population Selection (2017, methodology): “As with the work of (Joseph et al., 2016; Jabbari et al., 2016), we deﬁne the metric to be a measure of quality already present in the model (in our case, the CDF values of individuals) but unknown to the algorithm, except through samples.”