论文标题
为了最小公平的主动采样
Active Sampling for Min-Max Fairness
论文作者
论文摘要
我们提出了简单的主动采样和重新加权策略，以优化最低最大公平性，这些策略可应用于通过损失最小化学习的任何分类或回归模型。我们方法背后的关键直觉是在每个时间步中使用一个数据点，该数据点是在当前模型下更新模型下最差的组的数据点。实施的易用性和我们可靠的配方的普遍性使其成为改善弱势群体模型性能的有吸引力的选择。对于凸学习问题，例如线性或逻辑回归，我们提供了精细的分析，证明了与最小值公平解决方案的收敛速度。
We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model 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 disadvantaged groups. For convex learning problems, such as linear or logistic regression, we provide a fine-grained analysis, proving the rate of convergence to a min-max fair solution.
