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. We present a survey of the most commonly used loss functions for a wide range of different applications, divided into classification, regression, ranking, sample generation and energy based modelling. Overall, we introduce 33 different loss functions and we organise them into an intuitive taxonomy. Each loss function is given a theoretical backing and we describe where it is best used. This survey aims to provide a reference of the most essential loss functions for both beginner and advanced machine learning practitioners.
翻译:多数最先进的机器学习技术围绕损失功能的优化。 因此,确定适当的损失功能对于成功解决这一领域的问题至关重要。 我们为多种不同的应用对最常用的损失功能进行了调查,分为分类、回归、分级、抽样生成和基于能源的建模。 总的来说,我们引入了33个不同的损失功能,并将这些功能组织成直觉分类。 每个损失功能都得到了理论支持,我们描述了这些功能的最佳用途。 这次调查旨在为初学者和先进机器学习实践者提供最基本的损失功能的参考。