arXiv subjects

Nina M. Gottschling

Publications and source records attributed to Nina M. Gottschling.

4 recordsLinked to original sources

arXiv2026

Distribution-Agnostic Isocontour Confidence Bounds for Robust Uncertainty Visualization of Scalar Field Data

Uncertainty visualization has been shown to be pivotal for conveying the reliability of features extracted from scalar fields. Features represented by individual isocontours and mean isocontours lack an indication of spatial uncertainty, whereas spaghetti isocontour plots can become cluttered and difficult to interpret. Existing methods relying on specific distribution assumptions, such as Gaussian and nonparametric bootstrap, provide compact, clutter-free spatial confidence bounds but may underestimate uncertainty for ensembles with a limited number of samples. We introduce a robust, distribution-agnostic Hoeffding confidence band as a novel complementary (and not competitive) technique to mitigate potentially misleading uncertainty bounds that may arise from distribution-based assumptions. The approach constructs vertex-wise confidence bounds using Hoeffding's inequality and propagates them to generate isocontour confidence bands. Results on synthetic and real ensemble datasets show that the Hoeffding confidence bands are loose but accurately capture underlying true values that may be missed by the Gaussian and bootstrap alternatives, while remaining computationally efficient.

cs.CE↗

arXiv2026

Average Kernel Sizes -- Computable Sharp Accuracy Bounds for Inverse Problems

The reconstruction of an unknown quantity from noisy measurements is a mathematical problem relevant in most applied sciences, for example, in medical imaging, radar inverse scattering, or astronomy. This underlying mathematical problem is often an ill-posed (non-linear) reconstruction problem, referred to as an ill-posed inverse problem. To tackle such problems, there exist a myriad of methods to design approximate inverse maps, ranging from optimization-based approaches, such as compressed sensing, over Bayesian approaches, to data-driven techniques such as deep learning. For all stable approximate inverse maps, there are accuracy limits that are strictly larger than zero for ill-posed inverse problems, due to the accuracy-stability tradeoff [Gottschling et al., SIAM Review, 67.1 (2025)] and [Colbrook et al., Proceedings of the National Academy of Sciences, 119.12 (2022)]. The variety of methods that aim to solve such problems begs for a unifying approach to help scientists choose the approximate inverse map that obtains this theoretical optimum. Up to now there do not exist computable accuracy bounds to this optimum that are applicable to all inverse problems. We provide computable sharp accuracy bounds to the reconstruction error of solution methods to inverse problems. The bounds are method-independent and purely depend on the dataset of signals, the forward model of the inverse problem, and the noise model. To facilitate the use in scientific applications, we provide an algorithmic framework and an accompanying software library to compute these accuracy bounds. We demonstrate the validity of the algorithms on two inverse problems from different domains: fluorescence localization microscopy and super-resolution of multi-spectral satellite data. Computing the accuracy bounds for a problem before solving it, enables a fundamental shift towards optimizing datasets and forward models.

math.OC↗

arXiv2026

On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods

Artificial intelligence (AI) has transformed imaging inverse problems, from medical diagnostics to Earth observation. Yet deep neural networks can produce hallucinations, realistic-looking but incorrect details, undermining their reliability, especially when ground truth data is unavailable. We develop a theoretical framework showing that such hallucinations are not merely artifacts of particular models, but can arise from the ill-posed nature of the inverse problem itself. We derive necessary and sufficient conditions for hallucinations, together with computable bounds on their magnitude that depend only on the forward model. Building on this theory, we introduce algorithms to: (1) estimate the minimum hallucination magnitude achievable by any reconstruction model for a given input; (2) assess the faithfulness of reconstructed details by a given reconstruction model. Experiments across three imaging tasks demonstrate that our approach applies broadly, including to modern generative models, and provides a principled way to quantify and evaluate AI hallucinations.

stat.ML↗

arXiv2024

The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems

Methods inspired by Artificial Intelligence (AI) are starting to fundamentally change computational science and engineering through breakthrough performances on challenging problems. However, reliability and trustworthiness of such techniques is a major concern. In inverse problems in imaging, the focus of this paper, there is increasing empirical evidence that methods may suffer from hallucinations, i.e., false, but realistic-looking artifacts; instability, i.e., sensitivity to perturbations in the data; and unpredictable generalization, i.e., excellent performance on some images, but significant deterioration on others. This paper provides a theoretical foundation for these phenomena. We give mathematical explanations for how and when such effects arise in arbitrary reconstruction methods, with several of our results taking the form of `no free lunch' theorems. Specifically, we show that (i) methods that overperform on a single image can wrongly transfer details from one image to another, creating a hallucination, (ii) methods that overperform on two or more images can hallucinate or be unstable, (iii) optimizing the accuracy-stability trade-off is generally difficult, (iv) hallucinations and instabilities, if they occur, are not rare events, and may be encouraged by standard training, (v) it may be impossible to construct optimal reconstruction maps for certain problems. Our results trace these effects to the kernel of the forward operator whenever it is nontrivial, but also apply to the case when the forward operator is ill-conditioned. Based on these insights, our work aims to spur research into new ways to develop robust and reliable AI-based methods for inverse problems in imaging.

cs.LG↗