Solution of linear ill-posed problems by model selection and aggregation
Author(s) -
Felix Abramovich,
Daniela De Canditiis,
Marianna Pensky
Publication year - 2018
Publication title -
electronic journal of statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.482
H-Index - 54
ISSN - 1935-7524
DOI - 10.1214/18-ejs1447
Subject(s) - mathematics , estimator , model selection , selection (genetic algorithm) , oracle , mathematical optimization , inverse , linear model , contrast (vision) , inverse problem , statistics , computer science , artificial intelligence , mathematical analysis , geometry , software engineering
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.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom