Machine learning is increasingly used to inform decision making in sensitive situations
where decisions have consequential effects on individuals' lives. In these settings, in …

We review and reflect on fairness notions proposed in machine learning literature and make
an attempt to draw connections to arguments in moral and political philosophy, especially …

Machine learning is increasingly used to inform decision-making in sensitive situations
where decisions have consequential effects on individuals' lives. In these settings, in …

Although many fairness criteria have been proposed for decision making, their long-term
impact on the well-being of a population remains unclear. In this work, we study the …

Algorithmic risk assessments are used to inform decisions in a wide variety of high-stakes
settings. Often multiple predictive models deliver similar overall performance but differ …

We study an interesting variant of the stochastic multi-armed bandit problem, which we call
the Fair-MAB problem, where, in addition to the objective of maximizing the sum of expected …

Prediction-based decision-making systems are becoming increasingly prevalent in various
domains. Previous studies have demonstrated that such systems are vulnerable to runaway …

Optimization of conflicting functions is of paramount importance in decision making, and real
world applications frequently involve data that is uncertain or unknown, resulting in multi …

Contextual bandit algorithms have become widely used for recommendation in online
systems (eg marketplaces, music streaming, news), where they now wield substantial …

Algorithmic fairness in decision-making has been studied extensively in static settings where
one-shot decisions are made on tasks such as classification. However, in practice most …