发表机构
University of Chicago; University of Cambridge（芝加哥大学; 剑桥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一个通用框架，通过平均集成策略量化算法对各类数据扰动的稳定性，以协方差算子范数给出保证，并在实际扰动示例中提供更精确的稳定性保证。
AI 中文摘要
算法稳定性指的是算法对输入数据扰动不敏感的性质，其中扰动的类型可能因设置而异。在本工作中，我们开发了一个通用框架，用以量化任何通过平均定义的集成策略能在何种程度上为任何类型的数据扰动提供稳定性保证。我们的主要理论结果是对这种集成算法稳定性的保证，该保证以描述集成过程的某个协方差算子的范数形式给出。我们展示了我们的通用框架如何在几个实际感兴趣的扰动示例中产生可解释且直观的见解，并提供比从隐私考虑中获得的保证更为精确的保证。
英文摘要
Algorithmic stability refers to the property of an algorithm being insensitive to perturbations of the input data, where the type of perturbation may vary depending on the setting. In this work, we develop a general framework to quantify the extent to which any ensembling strategy defined via averaging can yield stability guarantees for any type of data perturbation. Our main theoretical result is a guarantee on the stability of this ensembled algorithm, given in terms of the norm of a certain covariance operator that describes the ensembling process. We show how our general framework yields interpretable and intuitive insights in several examples of perturbations of practical interest, and provides much sharper guarantees than those obtained from privacy considerations.
