78848

Автор(ы): 

Автор(ов): 

1

Параметры публикации

Тип публикации: 

Доклад

Название: 

Using Consistent Measures of Dependence and Symmetric Rényi Divergence in the Statistical Linearization

Электронная публикация: 

Да

ISBN/ISSN: 

2836-614X

DOI: 

10.1109/RusAutoCon61949.2024.10694249

Наименование конференции: 

  • 2024 International Russian Automation Conference (RusAutoCon)

Наименование источника: 

  • Proceedings of 2024 International Russian Automation Conference (RusAutoCon)

Обозначение и номер тома: 

Volume 1

Город: 

  • Piscataway

Издательство: 

  • IEEE

Год издания: 

2024

Страницы: 

https://ieeexplore.ieee.org/abstract/document/10694249
Аннотация
The article presents a new approach to identifying input/output mappings of stochastic systems. An essential component of this approach is the use of consistent measures of dependence of random variables. An essential component of this approach is consistent measures of dependence on random variables. The primary tool used in this approach is the symmetrical Rényi divergence. This measure allows us to consider both the properties of the Kullback-Leibler divergence and the Rényi entropy, making it especially useful in identifying the system and constructing sample estimates. One of the key advantages of this approach is its ability to work with dependent data. This is especially important when working with real systems, where inputs and outputs often have some degree of interconnection. The approach proposed in the article to identifying stochastic systems using consistent measures of dependence and symmetric Rényi divergence is significant and has great potential for application in various fields where the identification and analysis of dependencies between input and output variables is required.

Библиографическая ссылка: 

Чернышев К.Р. Using Consistent Measures of Dependence and Symmetric Rényi Divergence in the Statistical Linearization / Proceedings of 2024 International Russian Automation Conference (RusAutoCon). Piscataway: IEEE, 2024. Volume 1. С. https://ieeexplore.ieee.org/abstract/document/10694249.