2017

Calibrated Fairness in Bandits

Liu, Yang, Radanovic, Goran, Dimitrakakis, Christos et al.

Understand

We study fairness within the stochastic, \emph{multi-armed bandit} (MAB) decision making framework.

  • We adapt the fairness framework of "treating similar individuals similarly" to this setting.
  • Here, an `individual' corresponds to an arm and two arms are `similar' if they have a similar quality distribution.
  • First, we adopt a {\em smoothness constraint} that if two arms have a similar quality distribution then the probability of selecting each arm should be similar.

Built on

  • Near-optimal reinforcement learning in polynomial time

    Michael Kearns and Satinder Singh · 2002

    Earlier work this paper cites.

  • Action elimination and stopping conditions for the multi-armed and reinforcement learning problems

    Eyal Even-Dar, Shie Mannor, and Yishay Mansour · 2006

    Earlier work this paper cites.

  • Strictly proper scoring rules, prediction, and estimation

    Tilmann Gneiting and Adrian E Raftery · 2007

    Earlier work this paper cites.

  • Bayesian inference for plackett-luce ranking models

    John Guiver and Edward Snelson · 2009

    Earlier work this paper cites.

  • Label ranking methods based on the plackett-luce model

    Weiwei Cheng, Eyke Hüllermeier, and Krzysztof J Dembczynski · 2010

    Earlier work this paper cites.

  • Deterministic sequencing of exploration and exploitation for multi-armed bandit problems

    Original

    Sattar Vakili, Keqin Liu, and Qing Zhao · 2011

    Earlier work this paper cites.

Similar

  • Fairness through awareness

    Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel · 2012

    Cited alongside, same era.

  • The k-armed dueling bandits problem

    Yisong Yue, Josef Broder, Robert Kleinberg, and Thorsten Joachims · 2012

    Cited alongside, same era.

  • Online rank elicitation for plackett-luce: A dueling bandits approach

    Balázs Szörényi, Róbert Busa-Fekete, Adil Paul, and Eyke Hüllermeier · 2015

    Cited alongside, same era.

  • Fair prediction with disparate impact: A study of bias in recidivism prediction instruments

    Alexandra Chouldechova · 2016

    Cited alongside, same era.

  • Equality of opportunity in supervised learning

    Moritz Hardt, Eric Price, and Nati Srebro · 2016

    Cited alongside, same era.

  • Rawlsian fairness for machine learning

    Original

    Matthew Joseph, Michael Kearns, Jamie Morgenstern, Seth Neel, and Aaron Roth

    Cited in the paper.

  • Fairness in learning: Classic and contextual bandits

    Matthew Joseph, Michael Kearns, Jamie H Morgenstern, and Aaron Roth

    Cited in the paper.

Then

  • Fair learning in Markovian environments

    Shahin Jabbari, Matthew Joseph, Michael Kearns, Jamie Morgenstern, and Aaaron Roth · 2016

    Later among the works it cites.

  • Inherent trade-offs in the fair determination of risk scores

    Jon Kleinberg, Sendhil Mullainathan, and Manish Raghavan · 2016

    Later among the works it cites.

  • f f -divergence inequalities

    Igal Sason and Sergio Verdú · 2016

    Later among the works it cites.

  • Algorithmic decision making and the cost of fairness

    Sam Corbett-Davies, Emma Pierson, Avi Feller, Sharad Goel, and Aziz Huq · 2017

    Closest in time.

  • Subjective fairness: Fairness is in the eye of the beholder

    Original

    Christos Dimitrakakis, Yang Liu, David Parkes, and Goran Radanovic · 2017

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…