Active Sampling for Min-Max Fairness

We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model that is learned via loss minimization. The key intuition behind our approach is to use at each timestep a datapoint from the group that is worst off under the current model for updating the model. The ease of implementation and the generality of our robust formulation make it an attractive option for improving model performance on badly performing groups. For convex learning problems, such as linear or logistic regression, we provide a fine-grained analysis of our strategy, proving its rate of convergence to a min-max fair solution.