Work

Corrections to ``The Method of Gaps: Exact Expressions for the Generalization Error of Supervised Learning Algorithms''

Year: 2026

Type: erratum

Abstract: In this paper, a counterexample to Lemma 5 of the paper referenced in the title is provided. Consequently, the formulation of the method of data-driven gaps presented in the referenced paper relies on an additional assumption, namely, that the conditional distribution of the training dataset given the learned model has identical data-point-specific marginals. To overcome this limitation, a generalized formulation of the method of data-driven gaps that does not rely on Lemma 5 and does not require the training samples to be independent or identically distributed is presented. Through this formulation, the applicability of the method of data-driven gaps is extended to a broader class of data distributions and randomized learning algorithms.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26245

Author: Perlaza, Samir M.

Institution: Géométrie algébrique et applications à la théorie de l'information

Language: English

Topic: Machine Learning and Algorithms

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7222999207

Cites:

Cited by:

Related to: 10