In practice, the problems encountered in training NAS (Neural Architecture Search) are not simplex, but a series of combinations of difficulties are often faced(incorrect compensation estimation, curse of dimension, overfitting, high complexity, etc.). From the point of view for solving practical problems, this paper makes reference and improvement to the previous researches which only solve the single problem of NAS, and combines them into a practical technology flow. This paper propose a framework that decouples the network structure from the search space for operators. We use two BOHBs(Bayesian Optimization Hyperband) to search alternately in the vast network structure and operator search space. And then, we trained a GCN-baesd predictor using the feedback of the child model. This approach takes care of the dimension curse while improving efficiency. Considering that activation function and initialization are also important components of neural network, and can affect the generalization ability of the model. This paper introduced an activation function and an initialization method domain, join them to the operator search space to form a generalized search space, thus improving the generalization ability of the child model. At last, We applied our framework to neural architecture search and achieved significant improvements on multiple datasets.

翻译：在实践中,培训NAS(神经结构搜索)过程中遇到的问题并非简单,而是经常面临一系列困难的组合(不正确的补偿估计、尺寸的诅咒、过度装配、高度复杂等等)。从解决实际问题的角度来看,本文件参考并改进了以前只解决NAS单一问题的研究,并将这些研究纳入实用的技术流程。本文件提出了一个框架,将网络结构与操作员的搜索空间区分开来。我们使用两个BOHB(Bayesian Optimization Hyband)在庞大的网络结构和操作员搜索空间中轮流搜索。然后,我们利用儿童模型的反馈,培训了GCN-baesd预测器。这一方法在提高效率的同时,兼顾了这一层面的诅咒。考虑到激活功能和初始化也是神经网络的重要组成部分,并可能影响模型的普及能力。本文件引入了一个激活功能和初始化方法域,与操作员搜索空间一起形成一个普遍搜索空间,从而改进儿童模型的普及能力。我们最后应用了我们的重要搜索框架。