Related papers: Evaluating Trade-offs in Computer Vision Between A…
Many sets of ethics principles for responsible AI have been proposed to allay concerns about misuse and abuse of AI/ML systems. The underlying aspects of such sets of principles include privacy, accuracy, fairness, robustness,…
Machine learning models are often personalized with categorical attributes that are protected, sensitive, self-reported, or costly to acquire. In this work, we show models that are personalized with group attributes can reduce performance…
Group fairness, a class of fairness notions that measure how different groups of individuals are treated differently according to their protected attributes, has been shown to conflict with one another, often with a necessary cost in loss…
Machine learning tasks may admit multiple competing models that achieve similar performance yet produce conflicting outputs for individual samples -- a phenomenon known as predictive multiplicity. We demonstrate that fairness interventions…
The possible risk that AI systems could promote discrimination by reproducing and enforcing unwanted bias in data has been broadly discussed in research and society. Many current legal standards demand to remove sensitive attributes from…
Consider a pair of random variables $(X,Y)$ distributed according to a given joint distribution $p_{XY}$. A curator wishes to maximally disclose information about $Y$, while limiting the information leakage incurred on $X$. Adopting mutual…
This study investigates the trade-offs between fairness, privacy, and utility in image classification using machine learning (ML). Recent research suggests that generalization techniques can improve the balance between privacy and utility.…
Group fairness and privacy are fundamental aspects in designing trustworthy machine learning models. Previous research has highlighted conflicts between group fairness and different privacy notions. We are the first to demonstrate the…
Explicit and implicit bias clouds human judgement, leading to discriminatory treatment of minority groups. A fundamental goal of algorithmic fairness is to avoid the pitfalls in human judgement by learning policies that improve the overall…
Fairness emerged as an important requirement to guarantee that Machine Learning (ML) predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent subjectivity…
The objective of machine learning is to extract useful information from data, while privacy is preserved by concealing information. Thus it seems hard to reconcile these competing interests. However, they frequently must be balanced when…
Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…
Irrespective of the specific definition of fairness in a machine learning application, pruning the underlying model affects it. We investigate and document the emergence and exacerbation of undesirable per-class performance imbalances,…
As machine learning algorithms have been widely deployed across applications, many concerns have been raised over the fairness of their predictions, especially in high stakes settings (such as facial recognition and medical imaging). To…
Strategic learning studies how decision rules interact with agents who may strategically change their inputs/features to achieve better outcomes. In standard settings, models assume that the decision-maker's sole scope is to learn a…
In this paper, we investigate tradeoffs among differential privacy (DP) and several important voting axioms: Pareto efficiency, SD-efficiency, PC-efficiency, Condorcet consistency, and Condorcet loser criterion. We provide upper and lower…
Real-world applications of machine learning tools in high-stakes domains are often regulated to be fair, in the sense that the predicted target should satisfy some quantitative notion of parity with respect to a protected attribute.…
We propose a control-theoretic interpretation of recommender systems and use this perspective to analyze how fairness interventions shape long-term system behavior. Fairness concerns arise for both users and creators, ranging from opinion…
Algorithm designers increasingly optimize not only for accuracy, but also for the fairness of the algorithm across pre-defined groups. We study the tradeoff between fairness and accuracy for any given set of inputs to the algorithm. We…
Machine learning algorithms are now frequently used in sensitive contexts that substantially affect the course of human lives, such as credit lending or criminal justice. This is driven by the idea that `objective' machines base their…