Black-box tests for algorithmic stability.
Black-box tests for algorithmic stability.
复制标题
算法稳定性的黑盒测试。
DOI：
10.1093/imaiai/iaad039
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Barber,RinaFoygel
中科院分区：
文献类型：
--
作者：
Kim,Byol;Barber,RinaFoygel
算法稳定性是学习理论中的一个概念，它表示输入数据的变化（例如删除单个数据点）可能影响回归算法的输出的程度。了解算法的稳定性属性通常对于许多下游应用程序很有用，例如，众所周知，稳定性会带来理想的泛化属性和预测推理保证。然而，目前在实践中使用的许多现代算法过于复杂，无法对其稳定性特性进行理论分析，因此我们只能尝试通过对算法在各种数据集上的行为进行实证探索来建立这些特性。在这项工作中，我们为这种黑盒测试制定了一个正式的统计框架，不对算法或数据分布进行任何假设，并为任何黑盒测试识别算法稳定性的能力建立了基本界限。
Algorithmic stability is a concept from learning theory that expresses the degree to which changes to the input data (e.g. removal of a single data point) may affect the outputs of a regression algorithm. Knowing an algorithm’s stability properties is often useful for many downstream applications—for example, stability is known to lead to desirable generalization properties and predictive inference guarantees. However, many modern algorithms currently used in practice are too complex for a theoretical analysis of their stability properties, and thus we can only attempt to establish these properties through an empirical exploration of the algorithm’s behaviour on various datasets. In this work, we lay out a formal statistical framework for this kind ofblack-box testingwithout any assumptions on the algorithm or the data distribution, and establish fundamental bounds on the ability of any black-box test to identify algorithmic stability.