Adaptive minimax optimality in statistical inverse problems via SOLIT -- Sharp Optimal Lepskii-Inspired Tuning
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929216584417280 |
|---|---|
| author | Li, Housen Werner, Frank |
| author_facet | Li, Housen Werner, Frank |
| contents | We consider statistical linear inverse problems in separable Hilbert spaces and filter-based reconstruction methods of the form $\hat f_α= q_α\left(T^*T\right)T^*Y$, where $Y$ is the available data, $T$ the forward operator, $\left(q_α\right)_{α\in \mathcal A}$ 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) $\mathbb E [\Vert \hat f_α- f^\dagger\Vert^2]$ w.r.t.~the true solution $f^\dagger$ is minimized. In this paper, we introduce the Sharp Optimal Lepski\uı-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 $\left(q_α\right)_{α\in \mathcal A}$ 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 Lepski\uı-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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_10356 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Adaptive minimax optimality in statistical inverse problems via SOLIT -- Sharp Optimal Lepskii-Inspired Tuning Li, Housen Werner, Frank Statistics Theory Numerical Analysis We consider statistical linear inverse problems in separable Hilbert spaces and filter-based reconstruction methods of the form $\hat f_α= q_α\left(T^*T\right)T^*Y$, where $Y$ is the available data, $T$ the forward operator, $\left(q_α\right)_{α\in \mathcal A}$ 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) $\mathbb E [\Vert \hat f_α- f^\dagger\Vert^2]$ w.r.t.~the true solution $f^\dagger$ is minimized. In this paper, we introduce the Sharp Optimal Lepski\uı-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 $\left(q_α\right)_{α\in \mathcal A}$ 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 Lepski\uı-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. |
| title | Adaptive minimax optimality in statistical inverse problems via SOLIT -- Sharp Optimal Lepskii-Inspired Tuning |
| topic | Statistics Theory Numerical Analysis |
| url | https://arxiv.org/abs/2304.10356 |