Reviews: Model Compression with Adversarial Robustness: A Unified Optimization Framework

This paper formulates a new problem and proposed a reasonable algorithm. However, I am not totally convinced the current jointly optimization is significantly better a two steps approach of (1) first do adversarial learning and then (2) compress the model by pruning and compression. As shown in Figure 2, the performance of the proposed method is almost the same as the two step approach (adversarial learning pruning). Moreover, the current paper could be improved in the following aspects: - eq (3): what about the non-conversational layers? I wish to see results of other adversarial learning. Is it possible to provide experiments for large neural networks?