Algorithmic stability via ensembling

2026-09-09

AI Summary

本文通过集成策略量化算法稳定性，对任何类型的数据扰动提供稳定性保证，并给出比隐私考虑更精确的保证。

Abstract

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.

Problem

• Algorithmic stability
• ensembling strategy
• data perturbation
• stability guarantees

Innovation

• algorithmic stability
• ensembling strategy
• covariance operator
• data perturbation