Leading approaches to algorithmic fairness and policy-induced distribution shift are often misaligned with long-term objectives in sequential settings. We aim to correct these shortcomings by ensuring that both the objective and fairness constraints account for policy-induced distribution shift. First, we motivate this problem using an example in which individuals subject to algorithmic predictions modulate their willingness to participate with the policy maker. Fairness in this example is measured by the variance of group participation rates. Next, we develop a method for solving the resulting constrained, non-linear optimization problem and prove that this method converges to a fair, locally optimal policy given first-order information. Finally, we experimentally validate our claims in a semi-synthetic setting.

While machine learning can myopically reinforce social inequalities, it may also be used to dynamically seek equitable outcomes. In this paper, we formalize long-term fairness as an online reinforcement learning problem for a policy affecting human populations. This formulation accommodates dynamical control objectives, such as achieving equitable population states, that cannot be incorporated into static formulations of fairness. We demonstrate that algorithmic solutions to the proposed fairness problem can adapt to unknown dynamics and, by sacrificing short-term incentives, drive the policy-population system towards more desirable equilibria. For the proposed setting, we develop an algorithm that adapts recent work in online learning and prove that this algorithm achieves simultaneous probabilistic bounds on cumulative loss and cumulative violations of fairness. In the classification setting subject to group fairness, we compare our proposed algorithm to several baselines, including the repeated retraining of myopic or distributionally robust classifiers, and to a deep reinforcement learning algorithm that lacks fairness guarantees. Our experiments model human populations according to evolutionary game theory and integrate real-world datasets.

Given an algorithmic predictor that is "fair"' on some source distribution, will it still be fair on an unknown target distribution that differs from the source within some bound? In this paper, we study the transferability of statistical group fairness for machine learning predictors (i.e., classifiers or regressors subject to bounded distribution shift. Such shifts may be introduced by initial training data uncertainties, user adaptation to a deployed predictor, dynamic environments, or the use of pre-trained models in new settings. Herein, we develop a bound that characterizes such transferability, flagging potentially inappropriate deployments of machine learning for socially consequential tasks. We first develop a framework for bounding violations of statistical fairness subject to distribution shift, formulating a generic upper bound for transferred fairness violations as our primary result. We then develop bounds for specific worked examples, focusing on two commonly used fairness definitions (i.e., demographic parity and equalized odds) and two classes of distribution shift (i.e., covariate shift and label shift). Finally, we compare our theoretical bounds to deterministic models of distribution shift and against real-world data, finding that we are able to estimate fairness violation bounds in practice, even when simplifying assumptions are only approximately satisfied.

Realistically---and equitably---modeling the dynamics of group-level disparities in machine learning remains an open problem. In particular, we desire models that do not suppose inherent differences between artificial groups of people---but rather endogenize disparities by appeal to unequal initial conditions of insular subpopulations. In this paper, agents each have a real-valued feature $X$ (e.g., credit score) informed by a ``true'' binary label $Y$ representing qualification (e.g., for a loan). Each agent alternately (1) receives a binary classification label $\hat{Y}$ (e.g., loan approval) from a Bayes-optimal machine learning classifier observing $X$ and (2) may update their qualification $Y$ by imitating successful strategies (e.g., seek a raise) within an isolated group $G$ of agents to which they belong. We consider the disparity of qualification rates $\Pr(Y=1)$ between different groups and how this disparity changes subject to a sequence of Bayes-optimal classifiers repeatedly retrained on the global population. We model the evolving qualification rates of each subpopulation (group) using the replicator equation, which derives from a class of imitation processes. We show that differences in qualification rates between subpopulations can persist indefinitely for a set of non-trivial equilibrium states due to uniformed classifier deployments, even when groups are identical in all aspects except initial qualification densities. We next simulate the effects of commonly proposed fairness interventions on this dynamical system along with a new feedback control mechanism capable of permanently eliminating group-level qualification rate disparities. We conclude by discussing the limitations of our model and findings and by outlining potential future work.