English

Solution of linear ill-posed problems by model selection and aggregation

Methodology 2017-10-31 v1 Statistics Theory Statistics Theory

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.

Keywords

Cite

@article{arxiv.1710.10921,
  title  = {Solution of linear ill-posed problems by model selection and aggregation},
  author = {Felix Abramovich and Daniela De Canditiis and Marianna Pensky},
  journal= {arXiv preprint arXiv:1710.10921},
  year   = {2017}
}

Comments

20 pages, 2 figures

R2 v1 2026-06-22T22:29:40.344Z