Learning Non-Discriminatory Predictors

By Blake E. Woodworth, Suriya Gunasekar, Mesrob I. Ohannessian, Nati Srebro. 2017

404 citations recorded by the source corpus.

Subfields: AI Ethics, Fairness & Society

How researchers see this paper

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

In AI Ethics, Fairness & Society

Citations in the corpus

A Survey on Bias and Fairness in Machine Learning (2019, methodology): “Domain Sub-domain Reference(s) Data Simpson’s Paradox [68] Machine learning Classification [65] [86] [49] [72] [120] [55] [130] [126] [59] [24] [127] Machine learning Regression [13] [1] Machine learning PCA [111] Machine learning Community detection [85] Machine learning Clustering [30] [7] Machine”
Fair Resource Allocation in Federated Learning (2019, background): “Another set of works optimize an objective subject to some fairness constraints during training time [3, 6, 18, 43, 46, 47, 9].”
Fairness Without Demographics in Repeated Loss Minimization (2018, background): “There has been extensive work (Barocas & Selbst, 2016) on guaranteeing fairness for classiﬁcation over a protected label through constraints such as equalized odds (Woodworth et al., 2017; Hardt et al., 2016), disparate impact (Feldman et al., 2015) and calibration (Kleinberg et al., 2017).”
Fairness Through Computationally-Bounded Awareness (2018, background): “Post-processing prediction models for fairness has been studied in a few contexts [25, 14, 18].”
Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness (2017, methodology): “Thematically, the most closely related piece of work is Zhang and Neill [2016], who also aim to audit classification algorithms for discrimination in subgroups that have not been pre-defined. Our work differs from theirs in a number of important ways. First, we audit the algorithm for common measure”
Statistical Equity: A Fairness Classification Objective (2020, background): “…on fair classiﬁcation also targets a wide variety of fairness deﬁnitions, such as equality of opportunity and equalized odds [Hardt et al., 2016, Woodworth et al., 2017], statistical parity [Agarwal et al., 2018], and subgroup fairness [Ustun, Liu, and Parkes, 2019], and their incorporation…”
Stable and Fair Classification (2019, background): “Another approach for fair classiﬁcation is to shift the decision boundary of a baseline classiﬁer, e.g., [28, 37, 34, 61, 73, 22].”
The Frontiers of Fairness in Machine Learning (2018, background): “Learning subject to statistical fairness constraints can also be computationally hard [WGOS17], although practical algorithms of various sorts are known [HPS16, ZVGG17, ABD + 18].”
Taking Advantage of Multitask Learning for Fair Classification (2018, background): “In recent years there has been a lot of interest in the problem of enhancing learning methods with “fairness” requirements, see [1– 4 8–10 12 17 19 20 22–26 28 30 31 35–39] and references therein.”
Fairness-aware Classification: Criterion, Convexity, and Bounds (2018, methodology): “[Woodworth et al. 2017] Woodworth, B.; Gunasekar, S.; Ohannessian, M. I.; and Srebro, N. 2017.”
An Empirical Study of Rich Subgroup Fairness for Machine Learning (2018, background): “These deﬁnitions are pervasive in large part because they are easy to check, although there are interesting computational challenges in learning subject to these constraints in the worst case — see e.g. Woodworth et al. [2017].”
On Fairness and Calibration (2017, background): “To mitigate issues such as these, the machine learning community has proposed different frameworks that attempt to quantify fairness in classification [2, 4, 8, 19, 26, 34, 37].”
A Convex Framework for Fair Regression (2017, positive): “Optimizing for accuracy subject to an equality of odds constraint was recently shown to be NP-hard [31]; work following this result presented eﬃcient heuristics for the problem [31, 34].”
A Reductions Approach to Fair Classification (2018, methodology): “Copyright 2018 by the author(s). methods, often by relaxing the desired deﬁnitions of fairness, and only enforcing weaker constraints, such as lack of correlation (e.g., Woodworth et al., 2017; Zafar et al., 2017; Johnson et al., 2016; Kamishima et al., 2011; Donini et al., 2018).”
A comparative study of fairness-enhancing interventions in machine learning (2018, background): “Recent work by Hardt et al. [13] and Woodworth et al. [32] explored the use of post-processing as a way to ensure fairness with respect to error profiles (see Section 6 for more on this).”
Fairness in Reinforcement Learning (2016, background): “Woodworth et al. [27] and Zafar et al. [28] further studied these notion theoretically and empirically.”
Fair Algorithms for Infinite and Contextual Bandits (2016, background): “See Section 4 for a complete explanation of the distribution-dependent constant c in the regret bound for the inﬁnite case. protected attribute (such as race) conditioned on the true outcome, and they and Woodworth et al. [2017] have studied the feasibility and possible relaxations thereof.”
Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goals (2018, methodology): “lly if the constraints are optimized on small datasets. 7.4 Open Questions on Generalization In some speciﬁc applications, the post-training correction approach using a separate validation dataset of Woodworth et al. (2017) can improve generalization performance. More generally, in Cotter et al. (20”
Empirical Risk Minimization under Fairness Constraints (2018, background): “Methods in the second family enforce fairness directly during the training step: [18, 19, 20, 3, 21, 22, 23, 24, 25, 26] are examples of this method which provide non-convex approaches to the solution of the problem or they derive consistency results just for the non-convex formulation resorting lat”