We propose a mutual information-based sufficient representation learning (MSRL) approach, which uses the variational formulation of the mutual information and leverages the approximation power of deep neural networks. MSRL learns a sufficient representation with the maximum mutual information with the response and a user-selected distribution. It can easily handle multi-dimensional continuous or categorical response variables. MSRL is shown to be consistent in the sense that the conditional probability density function of the response variable given the learned representation converges to the conditional probability density function of the response variable given the predictor. Non-asymptotic error bounds for MSRL are also established under suitable conditions. To establish the error bounds, we derive a generalized Dudley's inequality for an order-two U-process indexed by deep neural networks, which may be of independent interest. We discuss how to determine the intrinsic dimension of the underlying data distribution. Moreover, we evaluate the performance of MSRL via extensive numerical experiments and real data analysis and demonstrate that MSRL outperforms some existing nonlinear sufficient dimension reduction methods.
翻译:我们建议一种基于信息的相互充足代表性学习(MSRL)方法,该方法使用相互信息的变式配方,利用深神经网络的近似功率。MSRL通过反应和用户选择的分布,在最大相互信息中学习到足够的代表性,可以很容易地处理多维连续或绝对反应变量。MSRL显示反应变量的有条件概率密度功能是一致的,因为从所学的表达方式来看,该响应变量的有条件概率密度功能与响应变量的有条件概率密度功能相融合。MSRL的非抽取误差界限也是在适当条件下建立的。为了确定错误界限,我们从由深神经网络索引化的顺序二 U工艺中得出一个普遍的Dudley的不平等性,这个顺序可能具有独立的兴趣。我们讨论如何确定基本数据分布的内在层面。此外,我们通过广泛的数字实验和真实的数据分析来评估MSRL的性能,并证明MSRL超越了某些现有的非线性充分的减少维度的方法。