arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.03518cs.LGstat.ML
收藏

最大加权损失离散

Maximum Weighted Loss Discrepancy

Stanford University(斯坦福大学)

Fereshte Khani, Aditi Raghunathan, Percy Liang

摘要:

虽然机器学习算法擅长最小化群体的平均损失,但这可能导致群体内各组之间的损失之间存在很大差异。为了捕捉这种不平等,我们引入并研究了一个概念,我们称之为最大加权损失差异(MWLD),一个组的损失和人口的损失之间的最大(加权)差异。我们将MWLD与群体公平概念和人口变化的鲁棒性联系起来。然后,我们证明了MWLD满足以下三个性质:1)当所有组具有相等的权重时,统计上不可能估计MWLD。2)对于一个特定的家庭的加权函数,我们可以有效地估计MWLD。3)MWLD与损失方差有关,损失方差是在泛化界限中出现的量。我们估计MWLD与不同的加权函数在四个常见的数据集的公平性文献。我们最后表明,损失方差正则化可以将分类器的损失方差减半,从而减少MWLD,而不会显著降低准确性。

英文摘要:

Though machine learning algorithms excel at minimizing the average loss over a population, this might lead to large discrepancies between the losses across groups within the population. To capture this inequality, we introduce and study a notion we call maximum weighted loss discrepancy (MWLD), the maximum (weighted) difference between the loss of a group and the loss of the population. We relate MWLD to group fairness notions and robustness to demographic shifts. We then show MWLD satisfies the following three properties: 1) It is statistically impossible to estimate MWLD when all groups have equal weights. 2) For a particular family of weighting functions, we can estimate MWLD efficiently. 3) MWLD is related to loss variance, a quantity that arises in generalization bounds. We estimate MWLD with different weighting functions on four common datasets from the fairness literature. We finally show that loss variance regularization can halve the loss variance of a classifier and hence reduce MWLD without suffering a significant drop in accuracy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑