Most state-of-the-art machine learning techniques revolve around the optimisation of loss functions. Defining appropriate loss functions is therefore critical to successfully solving problems in this field. In this survey, we present a comprehensive overview of the most widely used loss functions across key applications, including regression, classification, generative modeling, ranking, and energy-based modeling. We introduce 43 distinct loss functions, structured within an intuitive taxonomy that clarifies their theoretical foundations, properties, and optimal application contexts. This survey is intended as a resource for undergraduate, graduate, and Ph.D. students, as well as researchers seeking a deeper understanding of loss functions.

翻译：大多数最先进的机器学习技术都围绕损失函数的优化展开。因此，定义合适的损失函数对于成功解决该领域的问题至关重要。在本综述中，我们对关键应用领域（包括回归、分类、生成建模、排序和基于能量的建模）中最广泛使用的损失函数进行了全面概述。我们介绍了43种不同的损失函数，并将其组织在一个直观的分类框架中，以阐明它们的理论基础、特性及最佳应用场景。本综述旨在为本科生、研究生、博士生以及寻求深入理解损失函数的研究人员提供一份参考资料。