42574

Автор(ы): 

Автор(ов): 

2

Параметры публикации

Тип публикации: 

Доклад

Название: 

Robust Versions of Principal Component Analysis

ISBN/ISSN: 

978-989-8533-66-1

Наименование конференции: 

  • International Conference on Big Data Analytics, Data Mining and Computational Intelligence (BigDaCI 2017, Lisbon, Portugal)

Наименование источника: 

  • Proceedings of the International Conference on Big Data Analytics, Data Mining and Computational Intelligence (BigDaCI 2017, Lisbon, Portugal)

Город: 

  • Lisbon

Издательство: 

  • IADIS Press

Год издания: 

2017

Страницы: 

247-254
Аннотация
The modern problems of optimization, estimation, signal processing, and image recognition deal with data of huge dimensions. It is important to develop effective methods and algorithms for such problems. An important idea is the construction of low-dimension approximations to large-scale data. One of the most popular methods for this purpose is the principal component analysis (PCA), which is, however, sensitive to outliers. There exist numerous robust versions of PCA, relying on sparsity ideas and l1 techniques. The present paper offers another approach to robust PCA exploiting Huber's functions and numerical implementation based on the Iterative Reweighted Least Squares (IRLS) method.

Библиографическая ссылка: 

Поляк Б.Т., Хлебников М.В. Robust Versions of Principal Component Analysis / Proceedings of the International Conference on Big Data Analytics, Data Mining and Computational Intelligence (BigDaCI 2017, Lisbon, Portugal). Lisbon, Portugal: IADIS Press, 2017. С. 247-254.