Some Expressions for the Variance of a Cross-Validation | Sciact - Система учета научной деятельности ИМ СО РАН

Some Expressions for the Variance of a Cross-Validation Научная публикация

Конференция

22nd All-Russian Conference with International Participation “Mathematical Methods of Pattern Recognition” , September 22–26, 2025
22-26 сент. 2025 , Муром

Журнал

Pattern Recognition and Image Analysis
ISSN: 1054-6618 , E-ISSN: 1555-6212

Вых. Данные

Год: 2026, Том: 36, Номер: 2, Страницы: 642-647 Страниц : 6 DOI: 10.1134/s1054661826700458

Авторы

Nedel’ko V.M. ¹

Организации

1	Sobolev Institute of Mathematics, Siberian Branch, Russian Academy of Sciences, 630090, Novosibirsk, Russian Federation

Информация о финансировании (1)

Министерство науки и высшего образования РФ

FWNF-2026-0005

Cross-validation is one of the main methods for assessing the quality of solutions in machine learning. However, it remains unknown which of its varieties gives the most accurate results. To answer this question, it is necessary to learn how to calculate the variance of a cross-validation estimate. In this study, we will obtain some useful expressions for this quantity, which, in particular, make it possible to estimate the influence of the number of folds in splitting the sample. In the study, the effect of sample stratification during cross-validation has also been evaluated. To obtain a more pronounced difference, it has been proposed to perform the estimate using a procedure that is, in a sense, the opposite of stratification.

Nedel’ko V.M.
Some Expressions for the Variance of a Cross-Validation
Pattern Recognition and Image Analysis. 2026. V.36. N2. P.642-647. DOI: 10.1134/s1054661826700458 WOS OpenAlex

Поступила в редакцию:	28 февр. 2026 г.
Принята к публикации:	17 мар. 2026 г.
Опубликована в печати:	6 сент. 2026 г.
Опубликована online:	6 сент. 2026 г.

≡ Web of science:	WOS:001869006800026
≡ OpenAlex:	W7210276216