This is repo corresponding to my paper: DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks.
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. 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 and illustrate that our framework debiases the regularized estimators and performs well, in terms of the post-selection inference and the generalization error.
Please cite our paper if you use DebiNet in your papers, as follows:
@inproceedings{xu2021debinet,
title={DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks},
author={Xu, Shiyun and Bu, Zhiqi},
booktitle={International Conference on Artificial Intelligence and Statistics},
pages={3097--3105},
year={2021},
organization={PMLR}
}