An Information-Theoretic Perspective on the Relationship Between Fairness and Accuracy

Our goal is to understand the so-called trade-off between fairness and accuracy. In this work, using a tool from information theory called Chernoff information, we derive fundamental limits on this relationship that explain why the accuracy on a given dataset often decreases as fairness increases. Novel to this work, we examine the problem of fair classification through the lens of a mismatched hypothesis testing problem, i.e., where we are trying to find a classifier that distinguishes between two "ideal" distributions but instead we are given two mismatched distributions that are biased. Based on this perspective, we contend that measuring accuracy with respect to the given (possibly biased) dataset is a problematic measure of performance. Instead one should also consider accuracy with respect to an ideal dataset that is unbiased. We formulate an optimization to find such ideal distributions and show that the optimization is feasible. Lastly, when the Chernoff information for one group is strictly less than another in the given dataset, we derive the information-theoretic criterion under which collection of more features can actually improve the Chernoff information and achieve fairness without compromising accuracy on the available data.

[1]  T. Kailath.  The Divergence and Bhattacharyya Distance Measures in Signal Selection , 1967 .

[2]  Robert D. Nowak,et al.  A Neyman-Pearson approach to statistical learning , 2005, IEEE Transactions on Information Theory.

[3]  R. Karandikar,et al.  Sankhyā, The Indian Journal of Statistics , 2006 .

[4]  Franco Turini,et al.  Discrimination-aware data mining , 2008, KDD.

[5]  Joachim M. Buhmann,et al.  The Balanced Accuracy and Its Posterior Distribution , 2010, 2010 20th International Conference on Pattern Recognition.

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

[7]  Jun Sakuma,et al.  Fairness-Aware Classifier with Prejudice Remover Regularizer , 2012, ECML/PKDD.

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

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

[10]  Gábor Lugosi,et al.  Concentration Inequalities - A Nonasymptotic Theory of Independence , 2013, Concentration Inequalities.

[11]  Daniel Berend,et al.  A finite sample analysis of the Naive Bayes classifier , 2015, J. Mach. Learn. Res..

[12]  Francesco Bonchi,et al.  Algorithmic Bias: From Discrimination Discovery to Fairness-aware Data Mining , 2016, KDD.

[13]  Alfred O. Hero,et al.  Empirically Estimable Classification Bounds Based on a Nonparametric Divergence Measure , 2014, IEEE Transactions on Signal Processing.

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

[15]  Matt J. Kusner,et al.  Counterfactual Fairness , 2017, NIPS.

[16]  Kush R. Varshney,et al.  Optimized Pre-Processing for Discrimination Prevention , 2017, NIPS.

[17]  Junpei Komiyama,et al.  Two-stage Algorithm for Fairness-aware Machine Learning , 2017, ArXiv.

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

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

[20]  Matt Fredrikson,et al.  Use Privacy in Data-Driven Systems: Theory and Experiments with Machine Learnt Programs , 2017, CCS.

[21]  Matt J. Kusner,et al.  When Worlds Collide: Integrating Different Counterfactual Assumptions in Fairness , 2017, NIPS.

[22]  Bernhard Schölkopf,et al.  Avoiding Discrimination through Causal Reasoning , 2017, NIPS.

[23]  Shai Ben-David,et al.  Empirical Risk Minimization under Fairness Constraints , 2018, NeurIPS.

[24]  John Langford,et al.  A Reductions Approach to Fair Classification , 2018, ICML.

[25]  Matt Fredrikson,et al.  Hunting for Discriminatory Proxies in Linear Regression Models , 2018, NeurIPS.

[26]  AmirEmad Ghassami,et al.  Fairness in Supervised Learning: An Information Theoretic Approach , 2018, 2018 IEEE International Symposium on Information Theory (ISIT).

[27]  Alexandra Chouldechova,et al.  A case study of algorithm-assisted decision making in child maltreatment hotline screening decisions , 2018, FAT.

[28]  Aditya Krishna Menon,et al.  The cost of fairness in binary classification , 2018, FAT.

[29]  Krishna P. Gummadi,et al.  A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual &Group Unfairness via Inequality Indices , 2018, KDD.

[30]  David Sontag,et al.  Why Is My Classifier Discriminatory? , 2018, NeurIPS.

[31]  Krishna P. Gummadi,et al.  Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making , 2018, NeurIPS.

[32]  Omer Reingold,et al.  Tracking and Improving Information in the Service of Fairness , 2019, EC.

[33]  Prasanna Sattigeri,et al.  On Fairness in Budget-Constrained Decision Making , 2019 .

[34]  Kush R. Varshney,et al.  Trustworthy machine learning and artificial intelligence , 2019, XRDS.

[35]  Silvia Chiappa,et al.  Path-Specific Counterfactual Fairness , 2018, AAAI.

[36]  Peter Kairouz,et al.  Learning Generative Adversarial RePresentations (GAP) under Fairness and Censoring Constraints , 2019, ArXiv.

[37]  R. C. Williamson,et al.  Fairness risk measures , 2019, ICML.

[38]  Karthikeyan Natesan Ramamurthy,et al.  Optimized Score Transformation for Fair Classification , 2019, AISTATS.