标题： 正交统计学习与自协调损失 显示英文标题

标题： Orthogonal Statistical Learning with Self-Concordant Loss

摘要： 正交统计学习和双重机器学习在存在干扰成分的情况下，已成为两阶段统计预测的通用框架。 我们建立了满足自协调性质的损失函数的正交统计学习方法的额外风险的非渐近界。 我们的界在维度因子上优于现有界，同时消除了强凸性的假设。 我们通过多个处理效应估计和广义部分线性建模的例子来说明这些结果。 显示英文摘要

摘要： Orthogonal statistical learning and double machine learning have emerged as general frameworks for two-stage statistical prediction in the presence of a nuisance component. We establish non-asymptotic bounds on the excess risk of orthogonal statistical learning methods with a loss function satisfying a self-concordance property. Our bounds improve upon existing bounds by a dimension factor while lifting the assumption of strong convexity. We illustrate the results with examples from multiple treatment effect estimation and generalized partially linear modeling.