Online Learning with an Unknown Fairness Metric

We consider the problem of online learning in the linear contextual bandits setting, but in which there are also strong individual fairness constraints governed by an unknown similarity metric. These constraints demand that we select similar actions or individuals with approximately equal probability (arXiv:1104.3913), which may be at odds with optimizing reward, thus modeling settings where profit and social policy are in tension. We assume we learn about an unknown Mahalanobis similarity metric from only weak feedback that identifies fairness violations, but does not quantify their extent. This is intended to represent the interventions of a regulator who "knows unfairness when he sees it" but nevertheless cannot enunciate a quantitative fairness metric over individuals. Our main result is an algorithm in the adversarial context setting that has a number of fairness violations that depends only logarithmically on $T$, while obtaining an optimal $O(\sqrt{T})$ regret bound to the best fair policy.

[1]  Alexandra Chouldechova,et al.  Fair prediction with disparate impact: A study of bias in recidivism prediction instruments , 2016, Big Data.

[2]  Krishna P. Gummadi,et al.  Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment , 2016, WWW.

[3]  Aaron Roth,et al.  Fairness in Learning: Classic and Contextual Bandits , 2016, NIPS.

[4]  Guy N. Rothblum,et al.  Fairness Through Computationally-Bounded Awareness , 2018, NeurIPS.

[5]  Guy N. Rothblum,et al.  Calibration for the (Computationally-Identifiable) Masses , 2017, ArXiv.

[6]  Renato Paes Leme,et al.  Multidimensional Binary Search for Contextual Decision-Making , 2016, EC.

[7]  Nathan Srebro,et al.  Equality of Opportunity in Supervised Learning , 2016, NIPS.

[8]  Seth Neel,et al.  Fair Algorithms for Infinite and Contextual Bandits , 2016, 1610.09559.

[9]  Toniann Pitassi,et al.  Learning Fair Representations , 2013, ICML.

[10]  Seth Neel,et al.  Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness , 2017, ICML.

[11]  Suresh Venkatasubramanian,et al.  On the (im)possibility of fairness , 2016, ArXiv.

[12]  Josep Domingo-Ferrer,et al.  A Methodology for Direct and Indirect Discrimination Prevention in Data Mining , 2013, IEEE Transactions on Knowledge and Data Engineering.

[13]  Brian Kulis,et al.  Metric Learning: A Survey , 2013, Found. Trends Mach. Learn..

[14]  Guy N. Rothblum,et al.  Probably Approximately Metric-Fair Learning , 2018, ICML.

[15]  Yang Liu,et al.  Calibrated Fairness in Bandits , 2017, ArXiv.

[16]  Nisheeth K. Vishnoi,et al.  An Algorithmic Framework to Control Bias in Bandit-based Personalization , 2018, ArXiv.

[17]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[18]  Aaron Roth,et al.  Fairness in Reinforcement Learning , 2016, ICML.

[19]  Csaba Szepesvári,et al.  Improved Algorithms for Linear Stochastic Bandits , 2011, NIPS.

[20]  Jon M. Kleinberg,et al.  Inherent Trade-Offs in the Fair Determination of Risk Scores , 2016, ITCS.

[21]  Toon Calders,et al.  Data preprocessing techniques for classification without discrimination , 2011, Knowledge and Information Systems.

[22]  W. Hoeffding.  Probability Inequalities for sums of Bounded Random Variables , 1963 .

[23]  M. Kearns,et al.  Fairness in Criminal Justice Risk Assessments: The State of the Art , 2017, Sociological Methods & Research.

[24]  Inderjit S. Dhillon,et al.  Online Metric Learning and Fast Similarity Search , 2008, NIPS.