17617

Автор(ы): 

Автор(ов): 

4

Параметры публикации

Тип публикации: 

Доклад

Название: 

On the accuracy of l1-filtering of signals with block-sparse structure

Электронная публикация: 

Да

ISBN/ISSN: 

1049-5258

Наименование конференции: 

  • 25th Annual Conference on Neural Information Processing Systems (NIPS-2011, Granada, Spain)

Наименование источника: 

  • Proceedings of the 25th Annual Conference on Neural Information Processing Systems (NIPS-2011, Granada, Spain)

Город: 

  • Granada, Spain

Издательство: 

  • MIT Press

Год издания: 

2011

Страницы: 

1260-1268, http://books.nips.cc/nips24.html
Аннотация
We discuss new methods for the recovery of signals with block-sparse structure, based on l1-minimization. Our emphasis is on the efficiently computable error bounds for the recovery routines. We optimize these bounds with respect to the method parameters to construct the estimators with improved statistical properties. We justify the proposed approach with an oracle inequality which links the properties of the recovery algorithms and the best estimation performance.

Библиографическая ссылка: 

Юдицкий А.Б., Карзан Ф., Немировский А.С., Поляк Б.Т. On the accuracy of l1-filtering of signals with block-sparse structure / Proceedings of the 25th Annual Conference on Neural Information Processing Systems (NIPS-2011, Granada, Spain). Granada, Spain: MIT Press, 2011. С. 1260-1268, http://books.nips.cc/nips24.html.