Four-step Basis Pursuit with Applications
| Authors | |
|---|---|
| Year of publication | 2007 |
| Type | Article in Proceedings |
| Conference | Strobl07 Trends in Harmonic Analysis, June 18-22, 2007 |
| MU Faculty or unit | |
| Citation | |
| Web | Poster Strobl07 |
| Field | Applied statistics, operation research |
| Keywords | approximation; Basis Pursuit; sparsity; ROC estimators; smoothing; forecasting; ARMA models; air pollution |
| Description | A computationally intensive sparse parameter estimation technique based on a four-step modification of the Basis Pursuit Algorithm is presented (BPA4). In addition to some minimal theoretical background the contribution demonstrates performance and flexibility of BPA4 on four problems coming from completely diverse application fields: kernel approximation and smoothing, improved time series forecasting within an overcomplete stochastic frame of type ARMA, analysis of air pollution by suspended particulate matter and ROC curve estimation. This new computationally intensive approach allowed us to reliably identify nearly zero parameters in the respective model and thus to find numerically stable sparse parameter estimates. |
| Related projects: |