Recent work has shown that a much simpler model, simple graph convolution (SGC) (Wu et al., 2019),iscompetitivewithGCNs incommon graph machine learning benchmarks.

A classical problem that fits in the framework of (1) is the best subset selection problem in linear regression [6,20].

Machine learning models are famously vulnerable to adversarial attacks: small ad-hoc perturbations of the data that can catastrophically alter the model predictions.

In this paper, we will give the non-asymptotic convergence rate of the prediction error in high-dimensional adversarial training.