EZNAS: Evolving Zero-Cost Proxies For Neural Architecture Scoring Y ash Akhauri 1 J. Pablo Muñoz

NASBench-201 consists of 15,625 neural networks trained on the CIFAR-10, CIFAR-100 and ImageNet-16-120 datasets. Neural Networks in Network Design Spaces (NDS) uses the DARTS Liu et al. [2019] The networks are comprised of cells sampled from each of AmoebaNet Real et al. [2019], There exists approximately 5000 neural network architectures in each NDS design space. Our initial attempts at discovering ZC-NASMs took a different approach to program representation. To store intermediate scalars generated by the program, we allocate 20 memory addresses. ID and the third and fourth integers provide the read addresses for the operation.