Abstract
We consider a general statistical linear inverse problem, where the solution is represented via a known (possibly overcomplete) dictionary that allows its sparse representation. We propose two different approaches. A model selection estimator selects a single model by minimizing the penalized empirical risk over all possible models. By contrast with direct problems, the penalty depends on the model itself rather than on its size only as for complexity penalties. A Q-aggregate estimator averages over the entire collection of estimators with properly chosen weights. Under mild conditions on the dictionary, we establish oracle inequalities both with high probability and in expectation for the two estimators. Moreover, for the latter estimator these inequalities are sharp. The proposed procedures are implemented numerically and their performance is assessed by a simulation study.
| Original language | English GB |
|---|---|
| Pages (from-to) | 1822-1841 |
| Number of pages | 20 |
| Journal | Electronic Journal of Statistics |
| Volume | 12 |
| Issue number | 1 |
| DOIs | |
| State | Published - 2018 |
Keywords
- Aggregation
- Ill-posed linear inverse problem
- Model selection
- Oracle inequality
- Overcomplete dictionary
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty
Fingerprint
Dive into the research topics of 'Solution of linear ill-posed problems by model selection and aggregation'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver