We perform our experiments on both CIFAR-10 and ImageNet. The images are normalized by mean and standard deviation. The images are normalized by mean and standard deviation. Concretely, the super-net for search is composed of 6 normal cells and 2 reduction cells, and has an initial number of channels of 16. Each cell has 6 nodes.

Current gradient-based NAS methods commonly ignore the constraint of sparsity in the search phase, but project the optimized solution onto a sparse one by post-processing.

We thank all reviewers for the valuable comments. Sufficient to explore the entire search space? The proportion of explored architectures is decided by how many architectures are covered by the search process. We count how many different architectures are covered in the 50 epochs. This shows that there is not a significant difference.

We perform our experiments on both CIFAR-10 and ImageNet. The images are normalized by mean and standard deviation. The images are normalized by mean and standard deviation. Concretely, the super-net for search is composed of 6 normal cells and 2 reduction cells, and has an initial number of channels of 16. Each cell has 6 nodes.

Current gradient-based NAS methods commonly ignore the constraint of sparsity in the search phase, but project the optimized solution onto a sparse one by post-processing.