Optimizing the hyperparameters and architecture of a neural network is a long yet necessary phase in the development of any new application. This consuming process can benefit from the elaboration of strategies designed to quickly discard low quality configurations and focus on more promising candidates. This work aims at enhancing HyperNOMAD, a library that adapts a direct search derivative-free optimization algorithm to tune both the architecture and the training of a neural network simultaneously, by targeting two keys steps of its execution and exploiting cheap approximations in the form of static surrogates to trigger the early stopping of the evaluation of a configuration and the ranking of pools of candidates. These additions to HyperNOMAD are shown to improve on its resources consumption without harming the quality of the proposed solutions.
翻译:优化神经网络的超参数和结构是开发任何新应用的漫长而必要的阶段,这一消耗过程可以受益于制定战略,以迅速抛弃低质量配置并将重点放在更有希望的候选人上,这项工作的目的是加强HyperNOMAD,这是一个图书馆,该图书馆将直接搜索无衍生物优化算法调整成一种无衍生物优化算法,以同时调和神经网络的结构和培训,具体针对其实施的两个关键步骤,利用静态代孕形式的廉价近似物,以触发尽早停止对组合的评估和对候选人集合的排名,HyperNOMAD的添加表明,在不损害拟议解决方案质量的情况下,改善资源消耗情况。