The evolutionary algorithm (EA) is a nature-inspired population-based search method that works on Darwinian principles of natural selection. Due to its strong search capability and simplicity of implementation, EA has been successfully applied to solve many complex optimization problems, which cannot be easily solved by traditional exact mathematical approaches, such as linear programming, quadratic programming, and convex optimization. Despite its great success, it is worth noting that traditional EA solvers start the search from scratch by assuming zero prior knowledge about the task at hand. However, as problems seldom exist in isolation, solving one problem may yield useful information for solving other related problems. There has been growing interest in conducting research on evolutionary transfer optimization (ETO) in recent years: a paradigm that integrates EA solvers with knowledge learning and transfer across related domains to achieve better optimization efficiency and performance. This paper provides an overview of existing works of ETO based on the type of problems being solved by these methods, which are ETO for Optimization in Uncertain Environment, ETO for Multitask Optimization, ETO for Complex Optimization, ETO for Multi/Many-Objective Optimization, and ETO for Machine Learning Applications. The paper also highlights some of the challenges faced in this emerging research field of computational intelligence and discusses some promising future research directions in ETO. It is hoped that the study presented in this paper can help to inspire the development of more advanced ETO methods and applications.

中文翻译：

---

进化转移优化——进化计算研究的新前沿

进化算法 (EA) 是一种受自然启发的基于种群的搜索方法，适用于达尔文的自然选择原则。由于其强大的搜索能力和实现的简单性，EA 已成功应用于解决许多复杂的优化问题，这些问题是传统精确数学方法无法轻易解决的，例如线性规划、二次规划和凸优化。尽管取得了巨大的成功，但值得注意的是，传统的 EA 求解器通过假设手头任务的先验知识为零从头开始搜索。然而，由于问题很少孤立存在，解决一个问题可能会为解决其他相关问题提供有用的信息。近年来，人们对进行进化转移优化 (ETO) 的研究越来越感兴趣：一种将 EA 求解器与相关领域的知识学习和转移相结合的范例，以实现更好的优化效率和性能。本文根据这些方法解决的问题类型概述了 ETO 的现有工作，这些方法是用于不确定环境优化的 ETO、用于多任务优化的 ETO、用于复杂优化的 ETO、用于多/多目标优化的 ETO，和用于机器学习应用程序的 ETO。该论文还强调了这个新兴的计算智能研究领域面临的一些挑战，并讨论了 ETO 的一些有前途的未来研究方向。希望本文提出的研究有助于激发更先进的 ETO 方法和应用的开发。