Adaptive minimax optimality in statistical inverse problems via SOLIT—Sharp Optimal Lepskiĭ-Inspired Tuning
Open Access
- 27 December 2023
- journal article
- research article
- Published by IOP Publishing in Inverse Problems
- Vol. 40 (2) , 025005
Abstract
We consider statistical linear inverse problems in separable Hilbert spaces and filter-based reconstruction methods of the form f ˆ α = q α T ∗ T T ∗ Y , where Y is the available data, T the forward operator, q α α ∈ A an ordered filter, and α > 0 a regularization parameter. Whenever such a method is used in practice, α has to be appropriately chosen. Typically, the aim is to find or at least approximate the best possible α in the sense that mean squared error (MSE) E [ ∥ f ˆ α − f † ∥ 2 ] w.r.t. the true solution f † is minimized. In this paper, we introduce the Sharp Optimal Lepskiĭ-Inspired Tuning (SOLIT) method, which yields an a posteriori parameter choice rule ensuring adaptive minimax rates of convergence. It depends only on Y and the noise level σ as well as the operator T and the filter q α α ∈ A and does not require any problem-dependent tuning of further parameters. We prove an oracle inequality for the corresponding MSE in a general setting and derive the rates of convergence in different scenarios. By a careful analysis we show that no other a posteriori parameter choice rule can yield a better performance in terms of the order of the convergence rate of the MSE. In particular, our results reveal that the typical understanding of Lepskiĭ-type methods in inverse problems leading to a loss of a log factor is wrong. In addition, the empirical performance of SOLIT is examined in simulations.Keywords
All Related Versions
Funding Information
- Deutsche Forschungsgemeinschaft (DFG Collaborative Research Center 1456)
This publication has 31 references indexed in Scilit:
- Randomized algorithms for estimating the trace of an implicit symmetric positive semi-definite matrixJournal of the ACM, 2011
- Image deblurring with Poisson data: from cells to galaxiesInverse Problems, 2009
- A new chi-square approximation to the distribution of non-negative definite quadratic forms in non-central normal variablesComputational Statistics & Data Analysis, 2009
- Composite quantile regression and the oracle model selection theoryThe Annals of Statistics, 2008
- How general are general source conditions?Inverse Problems, 2008
- The Lepskii principle revisitedInverse Problems, 2006
- A Lepskij-type stopping rule for regularized Newton methodsInverse Problems, 2005
- Regularization without preliminary knowledge of smoothness and error behaviourEuropean Journal of Applied Mathematics, 2005
- Sharp adaptation for inverse problems with random noiseProbability Theory and Related Fields, 2002
- Variance Estimation for High-Dimensional Regression ModelsJournal of Multivariate Analysis, 2002