This work uses genetic programming to explore the space of continuous optimisers, with the goal of discovering novel ways of doing optimisation. In order to keep the search space broad, the optimisers are evolved from scratch using Push, a Turing-complete, general-purpose, language. The resulting optimisers are found to be diverse, and explore their optimisation landscapes using a variety of interesting, and sometimes unusual, strategies. Significantly, when applied to problems that were not seen during training, many of the evolved optimisers generalise well, and often outperform existing optimisers. This supports the idea that novel and effective forms of optimisation can be discovered in an automated manner. This paper also shows that pools of evolved optimisers can be hybridised to further increase their generality, leading to optimisers that perform robustly over a broad variety of problem types and sizes.

这项工作使用遗传编程来探索连续优化器的空间，目的是发现进行优化的新方法。为了保持广泛的搜索空间，优化器使用 Push（一种图灵完备的通用语言）从头开始演变。结果发现优化器是多种多样的，并使用各种有趣的、有时是不寻常的策略探索他们的优化前景。值得注意的是，当应用于训练期间未发现的问题时，许多进化的优化器可以很好地泛化，并且通常优于现有的优化器。这支持可以以自动化方式发现新颖有效的优化形式的想法。这篇论文还表明，进化优化器池可以混合以进一步增加它们的通用性，