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