Artificial Intelligence (AI) has driven innovations and created new opportunities across various sectors. However, leveraging domain-specific knowledge often requires automated tools to design and configure models effectively. In the case of Deep Neural Networks (DNNs), researchers and practitioners usually resort to Neural Architecture Search (NAS) approaches, which are resource- and time-intensive, requiring the training and evaluation of numerous candidate architectures. This raises sustainability concerns, particularly due to the high energy demands involved, creating a paradox: the pursuit of the most effective model can undermine sustainability goals. To mitigate this issue, zero-cost proxies have emerged as a promising alternative. These proxies estimate a model's performance without the need for full training, offering a more efficient approach. This paper addresses the challenges of model evaluation by automatically designing zero-cost proxies to assess DNNs efficiently. Our method begins with a randomly generated set of zero-cost proxies, which are evolved and tested using the NATS-Bench benchmark. We assess the proxies' effectiveness using both randomly sampled and stratified subsets of the search space, ensuring they can differentiate between low- and high-performing networks and enhance generalizability. Results show our method outperforms existing approaches on the stratified sampling strategy, achieving strong correlations with ground truth performance, including a Kendall correlation of 0.89 on CIFAR-10 and 0.77 on CIFAR-100 with NATS-Bench-SSS and a Kendall correlation of 0.78 on CIFAR-10 and 0.71 on CIFAR-100 with NATS-Bench-TSS.

翻译：人工智能（AI）推动了各领域的创新并创造了新的机遇。然而，有效利用领域特定知识通常需要自动化工具来设计和配置模型。对于深度神经网络（DNN），研究者和实践者通常采用神经架构搜索（NAS）方法，但这些方法资源消耗大、耗时长，需要训练和评估大量候选架构。这引发了可持续性担忧，特别是所涉及的高能耗需求造成了一个悖论：追求最高效的模型可能破坏可持续性目标。为缓解此问题，零成本代理已成为一种有前景的替代方案。这些代理无需完整训练即可评估模型性能，提供了一种更高效的途径。本文通过自动设计零成本代理来高效评估DNN，以应对模型评估的挑战。我们的方法从随机生成的一组零成本代理开始，利用NATS-Bench基准进行演化与测试。我们通过随机采样和搜索空间分层抽样两种方式评估代理的有效性，确保其能区分低性能与高性能网络并提升泛化能力。实验结果表明，在分层抽样策略上，我们的方法优于现有方案，与真实性能指标呈现强相关性：在NATS-Bench-SSS上获得CIFAR-10的肯德尔相关系数0.89和CIFAR-100的0.77；在NATS-Bench-TSS上获得CIFAR-10的0.78和CIFAR-100的0.71。