Adversarial robustness of a classifier describes its stability in classification under adversarial manipulations of the input.

We will often use variational optimization. When the variational family is not made explicit it means that the optimization is over all functions with the correct domain and codomain, e.g.

We propose a Bayesian generative model for incorporating prior domain knowledge into hierarchical topic modeling.

How would you go about checking if this proof is correct? One cumbersome way would be to directly refute the proof's claim, e.g., to demonstrate that actually