arXiv subjects

Christoph Kern

Publications and source records attributed to Christoph Kern.

26 records · Page 2Linked to original sources

arXiv2023

Minimizing Corners in Colored Rectilinear Grids

Given a rectilinear grid $G$, in which cells are either assigned a single color, out of $k$ possible colors, or remain white, can we color white grid cells of $G$ to minimize the total number of corners of the resulting colored rectilinear polygons in $G$? We show how this problem relates to hypergraph visualization, prove that it is NP-hard even for $k=2$, and present an exact dynamic programming algorithm. Together with a set of simple kernelization rules, this leads to an FPT-algorithm in the number of colored cells of the input. We additionally provide an XP-algorithm in the solution size, and a polynomial $\mathcal{O}(OPT)$-approximation algorithm.

cs.CG↗

arXiv2023

Network Navigation with Online Delays is PSPACE-complete

In public transport networks disruptions may occur and lead to travel delays. It is thus interesting to determine whether a traveler can be resilient to delays that occur unexpectedly, ensuring that they can reach their destination in time regardless. We model this as a game between the traveler and a delay-introducing adversary. We study the computational complexity of the problem of deciding whether the traveler has a winning strategy in this game. Our main result is that this problem is PSPACE-complete.

cs.CC↗

arXiv2022

Uncertainty-aware predictive modeling for fair data-driven decisions

Both industry and academia have made considerable progress in developing trustworthy and responsible machine learning (ML) systems. While critical concepts like fairness and explainability are often addressed, the safety of systems is typically not sufficiently taken into account. By viewing data-driven decision systems as socio-technical systems, we draw on the uncertainty in ML literature to show how fairML systems can also be safeML systems. We posit that a fair model needs to be an uncertainty-aware model, e.g. by drawing on distributional regression. For fair decisions, we argue that a safe fail option should be used for individuals with uncertain categorization. We introduce semi-structured deep distributional regression as a modeling framework which addresses multiple concerns brought against standard ML models and show its use in a real-world example of algorithmic profiling of job seekers.

stat.ML↗

arXiv2021

Fairness in Algorithmic Profiling: A German Case Study

Algorithmic profiling is increasingly used in the public sector as a means to allocate limited public resources effectively and objectively. One example is the prediction-based statistical profiling of job seekers to guide the allocation of support measures by public employment services. However, empirical evaluations of potential side-effects such as unintended discrimination and fairness concerns are rare. In this study, we compare and evaluate statistical models for predicting job seekers' risk of becoming long-term unemployed with respect to prediction performance, fairness metrics, and vulnerabilities to data analysis decisions. Focusing on Germany as a use case, we evaluate profiling models under realistic conditions by utilizing administrative data on job seekers' employment histories that are routinely collected by German public employment services. Besides showing that these data can be used to predict long-term unemployment with competitive levels of accuracy, we highlight that different classification policies have very different fairness implications. We therefore call for rigorous auditing processes before such models are put to practice.

cs.CY↗

arXiv2021

Distributive Justice and Fairness Metrics in Automated Decision-making: How Much Overlap Is There?

The advent of powerful prediction algorithms led to increased automation of high-stake decisions regarding the allocation of scarce resources such as government spending and welfare support. This automation bears the risk of perpetuating unwanted discrimination against vulnerable and historically disadvantaged groups. Research on algorithmic discrimination in computer science and other disciplines developed a plethora of fairness metrics to detect and correct discriminatory algorithms. Drawing on robust sociological and philosophical discourse on distributive justice, we identify the limitations and problematic implications of prominent fairness metrics. We show that metrics implementing equality of opportunity only apply when resource allocations are based on deservingness, but fail when allocations should reflect concerns about egalitarianism, sufficiency, and priority. We argue that by cleanly distinguishing between prediction tasks and decision tasks, research on fair machine learning could take better advantage of the rich literature on distributive justice.

stat.ML↗

arXiv2021

Global Trends and Predictors of Face Mask Usage During the COVID-19 Pandemic

Background: Guidelines and recommendations from public health authorities related to face masks have been essential in containing the COVID-19 pandemic. We assessed the prevalence and correlates of mask usage during the pandemic. Methods: We examined a total of 13,723,810 responses to a daily cross-sectional representative online survey in 38 countries who completed from April 23, 2020 to October 31, 2020 and reported having been in public at least once during the last seven days. The outcome was individual face mask usage in public settings, and the predictors were country fixed effects, country-level mask policy stringency, calendar time, individual sociodemographic factors, and health prevention behaviors. Associations were modelled using survey-weighted multivariable logistic regression. Findings: Mask-wearing varied over time and across the 38 countries. While some countries consistently showed high prevalence throughout, in other countries mask usage increased gradually, and a few other countries remained at low prevalence. Controlling for time and country fixed effects, sociodemographic factors (older age, female gender, education, urbanicity) and stricter mask-related policies were significantly associated with higher mask usage in public settings, while social behaviors considered risky in the context of the pandemic (going out to large events, restaurants, shopping centers, and socializing outside of the household) were associated with lower mask use. Interpretation: The decision to wear a face mask in public settings is significantly associated with sociodemographic factors, risky social behaviors, and mask policies. This has important implications for health prevention policies and messaging, including the potential need for more targeted policy and messaging design.

stat.AP↗

arXiv2019

A Longitudinal Framework for Predicting Nonresponse in Panel Surveys

Nonresponse in panel studies can lead to a substantial loss in data quality due to its potential to introduce bias and distort survey estimates. Recent work investigates the usage of machine learning to predict nonresponse in advance, such that predicted nonresponse propensities can be used to inform the data collection process. However, predicting nonresponse in panel studies requires accounting for the longitudinal data structure in terms of model building, tuning, and evaluation. This study proposes a longitudinal framework for predicting nonresponse with machine learning and multiple panel waves and illustrates its application. With respect to model building, this approach utilizes information from multiple waves by introducing features that aggregate previous (non)response patterns. Concerning model tuning and evaluation, temporal cross-validation is employed by iterating through pairs of panel waves such that the training and test sets move in time. Implementing this approach with data from a German probability-based mixed-mode panel shows that aggregating information over multiple panel waves can be used to build prediction models with competitive and robust performance over all test waves.

stat.ME↗

arXiv2019

Noise as Domain Shift: Denoising Medical Images by Unpaired Image Translation

We cast the problem of image denoising as a domain translation problem between high and low noise domains. By modifying the cycleGAN model, we are able to learn a mapping between these domains on unpaired retinal optical coherence tomography images. In quantitative measurements and a qualitative evaluation by ophthalmologists, we show how this approach outperforms other established methods. The results indicate that the network differentiates subtle changes in the level of noise in the image. Further investigation of the model's feature maps reveals that it has learned to distinguish retinal layers and other distinct regions of the images.

eess.IV↗