Black-box tests for algorithmic stability

Abstract

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 of black-box testing without 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.

Document Details

Document Type
Pub Defense Publication
Publication Date
Sep 18, 2023
Source ID
10.1093/imaiai/iaad039

Entities

People

  • Byol Kim
  • Rina Foygel Barber

Organizations

  • National Institutes of Health
  • National Science Foundation
  • Office of Naval Research
  • University of Chicago
  • University of Washington

Tags

Fields of Study

  • Computer science

Readers

  • Control Systems Engineering.
  • Neural Network Machine Learning.
  • Theoretical Analysis.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms