Learning to Pivot with Adversarial Networks
Learning to Pivot with Adversarial Networks
复制标题
DOI：
--
复制
发表时间：
2016-11
期刊：
影响因子：
--
通讯作者：
Gilles Louppe;M. Kagan;Kyle Cranmer
中科院分区：
文献类型：
--
作者：
Gilles Louppe;M. Kagan;Kyle Cranmer
已经提出了几种用于域自适应的技术，以考虑用于训练和测试的数据的分布的差异。这项工作的大部分集中在一个二进制域标签。类似的问题发生在科学背景下，可能有一个连续的家庭合理的数据生成过程与系统的不确定性的存在。稳健的推断是可能的，如果它是基于一个枢轴-一个数量的分布不依赖于参数化这个家庭的数据生成过程的滋扰参数的未知值。在这项工作中，我们介绍并推导了基于对抗网络的训练过程的理论结果，该训练过程用于在预测模型上执行关键属性（或者等价地，相对于连续属性的公平性）。该方法包括一个超参数，以控制准确性和鲁棒性之间的权衡。我们证明了这种方法的有效性与玩具的例子和粒子物理学的例子。
Several techniques for domain adaptation have been proposed to account for differences in the distribution of the data used for training and testing. The majority of this work focuses on a binary domain label. Similar problems occur in a scientific context where there may be a continuous family of plausible data generation processes associated to the presence of systematic uncertainties. Robust inference is possible if it is based on a pivot -- a quantity whose distribution does not depend on the unknown values of the nuisance parameters that parametrize this family of data generation processes. In this work, we introduce and derive theoretical results for a training procedure based on adversarial networks for enforcing the pivotal property (or, equivalently, fairness with respect to continuous attributes) on a predictive model. The method includes a hyperparameter to control the trade-off between accuracy and robustness. We demonstrate the effectiveness of this approach with a toy example and examples from particle physics.