arXiv subjects

Hoda Heidari

Publications and source records attributed to Hoda Heidari.

60 records · Page 4Linked to original sources

arXiv2019

Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making

We draw attention to an important, yet largely overlooked aspect of evaluating fairness for automated decision making systems---namely risk and welfare considerations. Our proposed family of measures corresponds to the long-established formulations of cardinal social welfare in economics, and is justified by the Rawlsian conception of fairness behind a veil of ignorance. The convex formulation of our welfare-based measures of fairness allows us to integrate them as a constraint into any convex loss minimization pipeline. Our empirical analysis reveals interesting trade-offs between our proposal and (a) prediction accuracy, (b) group discrimination, and (c) Dwork et al.'s notion of individual fairness. Furthermore and perhaps most importantly, our work provides both heuristic justification and empirical evidence suggesting that a lower-bound on our measures often leads to bounded inequality in algorithmic outcomes; hence presenting the first computationally feasible mechanism for bounding individual-level inequality.

cs.AI↗

arXiv2018

A Moral Framework for Understanding of Fair ML through Economic Models of Equality of Opportunity

We map the recently proposed notions of algorithmic fairness to economic models of Equality of opportunity (EOP)---an extensively studied ideal of fairness in political philosophy. We formally show that through our conceptual mapping, many existing definition of algorithmic fairness, such as predictive value parity and equality of odds, can be interpreted as special cases of EOP. In this respect, our work serves as a unifying moral framework for understanding existing notions of algorithmic fairness. Most importantly, this framework allows us to explicitly spell out the moral assumptions underlying each notion of fairness, and interpret recent fairness impossibility results in a new light. Last but not least and inspired by luck egalitarian models of EOP, we propose a new family of measures for algorithmic fairness. We illustrate our proposal empirically and show that employing a measure of algorithmic (un)fairness when its underlying moral assumptions are not satisfied, can have devastating consequences for the disadvantaged group's welfare.

cs.LG↗

arXiv2018

A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indices

Discrimination via algorithmic decision making has received considerable attention. Prior work largely focuses on defining conditions for fairness, but does not define satisfactory measures of algorithmic unfairness. In this paper, we focus on the following question: Given two unfair algorithms, how should we determine which of the two is more unfair? Our core idea is to use existing inequality indices from economics to measure how unequally the outcomes of an algorithm benefit different individuals or groups in a population. Our work offers a justified and general framework to compare and contrast the (un)fairness of algorithmic predictors. This unifying approach enables us to quantify unfairness both at the individual and the group level. Further, our work reveals overlooked tradeoffs between different fairness notions: using our proposed measures, the overall individual-level unfairness of an algorithm can be decomposed into a between-group and a within-group component. Earlier methods are typically designed to tackle only between-group unfairness, which may be justified for legal or other reasons. However, we demonstrate that minimizing exclusively the between-group component may, in fact, increase the within-group, and hence the overall unfairness. We characterize and illustrate the tradeoffs between our measures of (un)fairness and the prediction accuracy.

cs.LG↗

arXiv2017

A Convex Framework for Fair Regression

We introduce a flexible family of fairness regularizers for (linear and logistic) regression problems. These regularizers all enjoy convexity, permitting fast optimization, and they span the rang from notions of group fairness to strong individual fairness. By varying the weight on the fairness regularizer, we can compute the efficient frontier of the accuracy-fairness trade-off on any given dataset, and we measure the severity of this trade-off via a numerical quantity we call the Price of Fairness (PoF). The centerpiece of our results is an extensive comparative study of the PoF across six different datasets in which fairness is a primary consideration.

cs.LG↗

arXiv2017

Fairness in Criminal Justice Risk Assessments: The State of the Art

Objectives: Discussions of fairness in criminal justice risk assessments typically lack conceptual precision. Rhetoric too often substitutes for careful analysis. In this paper, we seek to clarify the tradeoffs between different kinds of fairness and between fairness and accuracy. Methods: We draw on the existing literatures in criminology, computer science and statistics to provide an integrated examination of fairness and accuracy in criminal justice risk assessments. We also provide an empirical illustration using data from arraignments. Results: We show that there are at least six kinds of fairness, some of which are incompatible with one another and with accuracy. Conclusions: Except in trivial cases, it is impossible to maximize accuracy and fairness at the same time, and impossible simultaneously to satisfy all kinds of fairness. In practice, a major complication is different base rates across different legally protected groups. There is a need to consider challenging tradeoffs.

stat.ML↗

arXiv2017

A General Framework for Evaluating Callout Mechanisms in Repeated Auctions

Motivated by online display ad exchanges, we study a setting in which an exchange repeatedly interacts with bidders who have quota, making decisions about which subsets of bidders are called to participate in ad-slot-specific auctions. A bidder with quota cannot respond to more than a certain number of calls per second. In practice, random throttling is the principal solution by which these constraints are enforced. Given the repeated nature of the interaction with its bidders, the exchange has access to data containing information about each bidder's segments of interest. This information can be utilized to design smarter callout mechanisms --- with the potential of improving the exchange's long-term revenue. In this work, we present a general framework for evaluating and comparing the performance of various callout mechanisms using historical auction data only. To measure the impact of a callout mechanism on long-term revenue, we propose a strategic model that captures the repeated interaction between the exchange and bidders. Our model leads us to two metrics for performance: immediate revenue impact and social welfare. Next we present an empirical framework for estimating these two metrics from historical data. For the baseline to compare against, we consider random throttling, as well as a greedy algorithm with certain theoretical guarantees. We propose several natural callout mechanisms and investigate them through our framework on both synthetic and real auction data. We characterize the conditions under which each heuristic performs well and show that, in addition to being computationally faster, in practice our heuristics consistently and significantly outperform the baselines.

cs.GT↗