Review for NeurIPS paper: The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification

Summary and Contributions: ***Update after author feedback*** Authors have addressed some of my concerns in feedback. After some reflection, I tend to *conditionally* increase my score (from 6 to 7) because of the following reasons: 1. they have provided partial evidence of assessment of variance in the experiments, showing that results are significant. It is crucial that such variance estimates are added to the paper and mentioned. There are strong arguments from a majority in the community, that not assessing variance arising from randomness is an experimental flaw. This is the *conditional* part of my score increase 2. The fact that they provide a separation oracle for the *tightest* convex relaxation of ReLU, helps to close down the chapter on such type of methods based on convex relaxations of activations.