Recent years have witnessed strong empirical performance of over-parameterized neural networks on various tasks and many advances in the theory, e.g. the universal approximation and provable convergence to global minimum. In this paper, we incorporate over-parameterized neural networks into semi-parametric models to bridge the gap between inference and prediction, especially in the high dimensional linear problem. By doing so, we can exploit a wide class of networks to approximate the nuisance functions and to estimate the parameters of interest consistently. Therefore, we may offer the best of two worlds: the universal approximation ability from neural networks and the interpretability from classic ordinary linear model, leading to both valid inference and accurate prediction. We show the theoretical foundations that make this possible and demonstrate with numerical experiments. Furthermore, we propose a framework, DebiNet, in which we plug-in arbitrary feature selection methods to our semi-parametric neural network. DebiNet can debias the regularized estimators (e.g. Lasso) and perform well, in terms of the post-selection inference and the generalization error.
翻译:近些年来,超参数神经网络在各种任务上取得了强有力的实证表现,理论也取得了许多进步,例如,普遍近似和可证实的趋同到全球最低程度。在本文件中,我们将超参数神经网络纳入半参数模型,以弥合推论和预测之间的差距,特别是在高维线性问题上。通过这样做,我们可以利用一系列广泛的网络,以近似干扰功能并一致地估计有关参数。因此,我们可以提供两个世界中最好的两个世界:神经网络的普遍近似能力和经典普通线性模型的可解释性,导致有效的推论和准确的预测。我们展示了使这一点成为可能的理论基础,并通过数字实验展示了这些理论基础。此外,我们提出了一个框架,即DebiNet,在这个框架中,我们可以将任意特征选择方法插入我们的半参数神经网络。DebiNet可以贬低正常的测算器(例如Lasso),并在选后推论和一般化错误方面表现良好。