DeepAI AI Chat
Log In Sign Up

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

by   Felix Abramovich, et al.
University of Central Florida
Tel Aviv University
Consiglio Nazionale delle Ricerche

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.


page 1

page 2

page 3

page 4


Oracle inequalities for computationally adaptive model selection

We analyze general model selection procedures using penalized empirical ...

Sharp oracle inequalities for stationary points of nonconvex penalized M-estimators

Many statistical estimation procedures lead to nonconvex optimization pr...

Sparse-penalized deep neural networks estimator under weak dependence

We consider the nonparametric regression and the classification problems...

Deviation optimal learning using greedy Q-aggregation

Given a finite family of functions, the goal of model selection aggregat...

Sparse Density Estimation with Measurement Errors

This paper aims to build an estimate of an unknown density of the data w...

Group Invariance and Computational Sufficiency

Statistical sufficiency formalizes the notion of data reduction. In the ...

Exponential Tail Local Rademacher Complexity Risk Bounds Without the Bernstein Condition

The local Rademacher complexity framework is one of the most successful ...