Frank Werner

Frank Werner, Thorsten Hohage

In this paper we study a Tikhonov-type method for ill-posed nonlinear operator equations $\gdag = F(\udag)$ where $\gdag$ is an integrable, non-negative function. We assume that data are drawn from a Poisson process with density $t\gdag$ where $t>0$ may be interpreted as an exposure time. Such problems occur in many photonic imaging applications including positron emission tomography, confocal fluorescence microscopy, astronomic observations, and phase retrieval problems in optics. Our approach uses a Kullback-Leibler-type data fidelity functional and allows for general convex penalty terms. We prove convergence rates of the expectation of the reconstruction error under a variational source condition as $t\to\infty$ both for an a priori and for a Lepski{\uı}-type parameter choice rule.

Thorsten Hohage, Frank Werner

We study Newton type methods for inverse problems described by nonlinear operator equations $F(u)=g$ in Banach spaces where the Newton equations $F'(u_n;u_{n+1}-u_n) = g-F(u_n)$ are regularized variationally using a general data misfit functional and a convex regularization term. This generalizes the well-known iteratively regularized Gauss-Newton method (IRGNM). We prove convergence and convergence rates as the noise level tends to 0 both for an a priori stopping rule and for a Lepski{\uı}-type a posteriori stopping rule. Our analysis includes previous order optimal convergence rate results for the IRGNM as special cases. The main focus of this paper is on inverse problems with Poisson data where the natural data misfit functional is given by the Kullback-Leibler divergence. Two examples of such problems are discussed in detail: an inverse obstacle scattering problem with amplitude data of the far-field pattern and a phase retrieval problem. The performence of the proposed method for these problems is illustrated in numerical examples.

Claudia König, Frank Werner, Thorsten Hohage

This paper is concerned with exponentially ill-posed operator equations with additive impulsive noise on the right hand side, i.e. the noise is large on a small part of the domain and small or zero outside. It is well known that Tikhonov regularization with an $L^1$ data fidelity term outperforms Tikhonov regularization with an $L^2$ fidelity term in this case. This effect has recently been explained and quantified for the case of finitely smoothing operators. Here we extend this analysis to the case of infinitely smoothing forward operators under standard Sobolev smoothness assumptions on the solution, i.e. exponentially ill-posed inverse problems. It turns out that high order polynomial rates of convergence in the size of the support of large noise can be achieved rather than the poor logarithmic convergence rates typical for exponentially ill-posed problems. The main tools of our analysis are Banach spaces of analytic functions and interpolation-type inequalities for such spaces. We discuss two examples, the (periodic) backwards heat equation and an inverse problem in gradiometry.

Vahid Kayvanfar, Hamed Baziyad, Shaya Sheikh et al.

Evaluating the efficiency of organizations and branches within an organization is a challenging issue for managers. Evaluation criteria allow organizations to rank their internal units, identify their position concerning their competitors, and implement strategies for improvement and development purposes. Among the methods that have been applied in the evaluation of bank branches, non-parametric methods have captured the attention of researchers in recent years. One of the most widely used non-parametric methods is the data envelopment analysis (DEA) which leads to promising results. However, the static DEA approaches do not consider the time in the model. Therefore, this paper uses a dynamic DEA (DDEA) method to evaluate the branches of a private Iranian bank over three years (2017-2019). The results are then compared with static DEA. After ranking the branches, they are clustered using the K-means method. Finally, a comprehensive sensitivity analysis approach is introduced to help the managers to decide about changing variables to shift a branch from one cluster to a more efficient one.

Housen Li, Frank Werner

We consider the statistical inverse problem to recover $f$ from noisy measurements $Y = Tf + σξ$ where $ξ$ is Gaussian white noise and $T$ a compact operator between Hilbert spaces. Considering general reconstruction methods of the form $\hat f_α= q_α\left(T^*T\right)T^*Y$ with an ordered filter $q_α$, we investigate the choice of the regularization parameter $α$ by minimizing an unbiased estimate of the predictive risk $\mathbb E\left[\Vert Tf - T\hat f_α\Vert^2\right]$. The corresponding parameter $α_{\mathrm{pred}}$ and its usage are well-known in the literature, but oracle inequalities and optimality results in this general setting are unknown. We prove a (generalized) oracle inequality, which relates the direct risk $\mathbb E\left[\Vert f - \hat f_{α_{\mathrm{pred}}}\Vert^2\right]$ with the oracle prediction risk $\inf_{α>0}\mathbb E\left[\Vert Tf - T\hat f_α\Vert^2\right]$. From this oracle inequality we are then able to conclude that the investigated parameter choice rule is of optimal order. Finally we also present numerical simulations, which support the order optimality of the method and the quality of the parameter choice in finite sample situations.

Jonas Dornbusch, Emanuel Pfarr, Florin-Alexandru Vasluianu et al.

Diffusion models have garnered considerable interest in computer vision, owing both to their capacity to synthesize photorealistic images and to their proven effectiveness in image reconstruction tasks. However, existing approaches fail to efficiently balance the high visual quality of diffusion models with the low distortion achieved by previous image reconstruction methods. Specifically, for the fundamental task of additive Gaussian noise removal, we first illustrate an intuitive method for leveraging pretrained diffusion models. Further, we introduce our proposed Linear Combination Diffusion Denoiser (LCDD), which unifies two complementary inference procedures - one that leverages the model's generative potential and another that ensures faithful signal recovery. By exploiting the inherent structure of the denoising samples, LCDD achieves state-of-the-art performance and offers controlled, well-behaved trade-offs through a simple scalar hyperparameter adjustment.

Katharina Proksch, Frank Werner, Axel Munk

In this paper we propose a multiscale scanning method to determine active components of a quantity $f$ w.r.t. a dictionary $\mathcal{U}$ from observations $Y$ in an inverse regression model $Y=Tf+ξ$ with linear operator $T$ and general random error $ξ$. To this end, we provide uniform confidence statements for the coefficients $\langle φ, f\rangle$, $φ\in \mathcal U$, under the assumption that $(T^*)^{-1} \left(\mathcal U\right)$ is of wavelet-type. Based on this we obtain a multiple test that allows to identify the active components of $\mathcal{U}$, i.e. $\left\langle f, φ\right\rangle \neq 0$, $φ\in \mathcal U$, at controlled, family-wise error rate. Our results rely on a Gaussian approximation of the underlying multiscale statistic with a novel scale penalty adapted to the ill-posedness of the problem. The scale penalty furthermore ensures weak convergence of the statistic's distribution towards a Gumbel limit under reasonable assumptions. The important special cases of tomography and deconvolution are discussed in detail. Further, the regression case, when $T = \text{id}$ and the dictionary consists of moving windows of various sizes (scales), is included, generalizing previous results for this setting. We show that our method obeys an oracle optimality, i.e. it attains the same asymptotic power as a single-scale testing procedure at the correct scale. Simulations support our theory and we illustrate the potential of the method as an inferential tool for imaging. As a particular application we discuss super-resolution microscopy and analyze experimental STED data to locate single DNA origami.