The paper entitled “Provably Bounding Neural Network Preimages” by Christopher Brix, Suhas Kotha (CMU), Huan Zhang (UIUC), Zico Kolter (CMU), Krishnamurthy (Dj) Dvijotham (Google DeepMind) has been accepted for publication in the thirty-seventh Conference on Neural Information Processing Systems. The paper presents a way to compute bounds on the preimage of the output of a neural network by transforming the problem such that it can be optimized by state-of-the-art tools for the forward verification of neural networks. Furthermore, it demonstrates how previously unused output constraints can be incorporated into regular forward verification queries. These approaches significantly improves both the precision and speed of the approximations for both applications.