Machkour, J. ; Alt, B. ; Muma, M. ; Zoubir, A. M. (2017)
The Outlier-Corrected-Data-Adaptive Lasso: A New Robust Estimator for the Independent Contamination Model.
25th European Signal Processing Conference (EUSIPCO 2017). Kos, Greece (28.08.-02.09.2017)
doi: 10.23919/EUSIPCO.2017.8081489
Conference or Workshop Item, Bibliographie
Abstract
Many of today's signal processing tasks consider sparse models where the number of explanatory variables exceeds the sample size. When dealing with real-world data, the presence of impulsive noise and outliers must also be accounted for. Accurate and robust parameter estimation and consistent variable selection are needed simultaneously. Recently, some popular robust methods have been adapted to such complex settings. Especially, in high dimensional settings, however, it is possible to have a single contaminated predictor being responsible for many outliers. The amount of outliers introduced by this predictor easily exceeds the breakdown point of any existing robust estimator. Therefore, we propose a new robust and sparse estimator, the Outlier-Corrected-Data-(Adaptive) Lasso (OCD-(A) Lasso). It simultaneously handles highly contaminated predictors in the dataset and performs well under the classical contamination model. In a numerical study, it outperforms competing Lasso estimators, at a largely reduced computational complexity compared to its robust counterparts.
| Item Type: | Conference or Workshop Item |
|---|---|
| Erschienen: | 2017 |
| Creators: | Machkour, J. ; Alt, B. ; Muma, M. ; Zoubir, A. M. |
| Type of entry: | Bibliographie |
| Title: | The Outlier-Corrected-Data-Adaptive Lasso: A New Robust Estimator for the Independent Contamination Model |
| Language: | English |
| Date: | 26 October 2017 |
| Publisher: | IEEE |
| Book Title: | 2017 25th European Signal Processing Conference (EUSIPCO) |
| Event Title: | 25th European Signal Processing Conference (EUSIPCO 2017) |
| Event Location: | Kos, Greece |
| Event Dates: | 28.08.-02.09.2017 |
| DOI: | 10.23919/EUSIPCO.2017.8081489 |
| URL / URN: | http://ieeexplore.ieee.org/document/8081489/ |
| Abstract: | Many of today's signal processing tasks consider sparse models where the number of explanatory variables exceeds the sample size. When dealing with real-world data, the presence of impulsive noise and outliers must also be accounted for. Accurate and robust parameter estimation and consistent variable selection are needed simultaneously. Recently, some popular robust methods have been adapted to such complex settings. Especially, in high dimensional settings, however, it is possible to have a single contaminated predictor being responsible for many outliers. The amount of outliers introduced by this predictor easily exceeds the breakdown point of any existing robust estimator. Therefore, we propose a new robust and sparse estimator, the Outlier-Corrected-Data-(Adaptive) Lasso (OCD-(A) Lasso). It simultaneously handles highly contaminated predictors in the dataset and performs well under the classical contamination model. In a numerical study, it outperforms competing Lasso estimators, at a largely reduced computational complexity compared to its robust counterparts. |
| Divisions: | 18 Department of Electrical Engineering and Information Technology 18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications > Bioinspired Communication Systems 18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications 18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications > Robust Data Science 18 Department of Electrical Engineering and Information Technology > Institute for Telecommunications > Signal Processing |
| Date Deposited: | 15 Mar 2017 11:42 |
| Last Modified: | 17 Apr 2024 12:07 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Send an inquiry |
Options (only for editors)
 |
Show editorial Details |
Drucken
Impressum