Adaptive minimax optimality in statistical inverse problems via SOLIT -- Sharp Optimal Lepskii-Inspired Tuning

We consider statistical linear inverse problems in separable Hilbert spaces and filter-based reconstruction methods of the form $\hat f_\alpha = q_\alpha \left(T^*T\right)T^*Y$, where $Y$ is the available data, $T$ the forward operator, $\left(q_\alpha\right)_{\alpha \in \mathcal A}$ an ordered filter, and $\alpha > 0$ a regularization parameter. Whenever such a method is used in practice, $\alpha$ has to be chosen appropriately. Typically, the aim is to find or at least approximate the best possible $\alpha$ in the sense that mean squared error (MSE) $\mathbb E [\Vert \hat f_\alpha - f^\dagger\Vert^2]$ w.r.t.~the true solution $f^\dagger$ is minimized. In this paper, we introduce the Sharp Optimal Lepski\u{\i}-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 $\sigma$ as well as the operator $T$ and the filter $\left(q_\alpha\right)_{\alpha \in \mathcal A}$ 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 convergence rate of the MSE. In particular, our results reveal that the typical understanding of Lepskiii-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.