Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Nadja Klein
Computer Science > Artificial Intelligence
[Submitted on 8 Sep 2026] Title:XAI-Arena: Can LLMs Assess the Quality of XAI Explanations?
[2603.26309] Semi-structured multi-state delinquency model for mortgage default
[Submitted on 27 Mar 2026] Title:Semi-structured multi-state delinquency model for mortgage default View a PDF of the paper titled Semi-structured multi-state delinquency model for mortgage default, by Victor Medina-Olivares and Wangzhen Xia and Stefan Lessmann and Nadja Klein View PDF HTML (experimental) Abstract:We propose a semi-structured discrete-time multi-state model to analyse mortgage delinquency transitions.
[2603.19977] Scalable and Robust Spatial Prediction via Multi-Resolution Ensembles of Predictive Processes
[Submitted on 20 Mar 2026 (v1), last revised 2 Oct 2026 (this version, v2)] View PDF HTML (experimental) Subjects: Methodology (stat.ME) Cite as: arXiv:2603.19977 [stat.ME] (or arXiv:2603.19977v2 [stat.ME] for this version) https://doi.org/10.48550/arXiv.2603.19977
Computer Science > Machine Learning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2602.05730] Depth as Prior Knowledge for Object Detection
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Jugend meets Politik: „Politiker Speed-Dating“ des Kreisjugendrings Miltenberg am 23.01.2026 im Jugendzentrum Miltenberg
Auf Einladung des Kreisjugendrings Miltenberg hatten die Parteien des aktuellen Kreistages die Möglichkeit, mit politikinteressierten Jugendlichen ins Gespräch zu kommen. Die AG Demokratie des KJR Miltenberg tat sich zu diesem Zweck mit dem Jugendzentrum Miltenberg zusammen, das die Räume des Zentrums gerne zur Verfügung stellte. Einige Jugendliche waren schon nachmittags im Jugendzentrum und tauschten sich über die Fragen aus, die sie den Politikerinnen und Politikern stellen wollen.
Kreisjugendring Miltenberg: Herbstvollversammlung 2025
Am Freitag, den 28.11.2025 trafen sich über 50 Delegierte und Gäste des Kreisjugendrings Miltenberg zur diesjährigen Herbstvollversammlung in der Narrhalla der Carnevalvereins Niederberg. Der offizielle Teil begann um 18:30 Uhr. Besonders begrüßt wurden von der Vorsitzenden Alison Wölfelschneider, die Vertreter des Landratsamts Stefan Adams sowie Emma Grimm, die die besten Grüße vom Landrat Bernd Schötterl im Gepäck hatten. Die Grüße vom Bezirksjugendring Unterfranken überbrachte Florian Bauer.
Deep Mixture of Linear Mixed Models for Complex Longitudinal Data
1 Introduction Longitudinal data play an important role in many biomedical applications [1, 2]. In their practical use, mixtures of linear mixed models (MLMMs) [3] are widely used for the analysis of longitudinal data for which observation times differ by subject, and in cases where there is a need to “borrow strength” between subjects in a flexible way.
Tatort Handy: Cyberkriminalität im Netz
Am 29.11. und am 30.11.2024 veranstaltet der KJR Miltenberg einen Vortrag zum Thema „Cyberkriminalität im Netz“. Inhaltlich sind beide Veranstaltungen gleich aufgebaut. Ihr erfahrt alles über Hackerangriffe, Cybermobbing, Präventionsmaßnahmen, was im Ernstfall zu tun ist und vieles mehr. Dieses Projekt wird aus dem „Demokratie-Budget“ des Bayerischen Staatsministeriums für Familie, Arbeit und Soziales durch den Bayerischen Jugendring gefördert. Dieser Inhalt gefällt Ihnen?
[2401.06523] Boosting Causal Additive Models
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Flexible Specification Testing in Quantile Regression Models
Abstract We propose three novel consistent specification tests for quantile regression models which generalize former tests in three ways. First, we allow the covariate effects to be quantile-dependent and non-linear. Second, we allow parameterizing the conditional quantile functions by appropriate basis functions, rather than parametrically. We are thereby able to test for general functional forms, while retaining linear effects as special cases.
[2305.06625] Dropout Regularization in Extended Generalized Linear Models based on Double Exponential Families
Even though dropout is a popular regularization technique, its theoretical properties are not fully understood. In this paper we study dropout regularization in extended generalized linear models based on double exponential families, for which the dispersion parameter can vary with the features.
Boosting multivariate structured additive distributional regression models
1 INTRODUCTION Many modern regression models relate certain characteristics of a univariate response distribution to explanatory variables. Examples include generalized additive models (GAMs)1, 2 and quantile regression models,3 where with the former the conditional expectation and with the latter conditional quantiles of a univariate response distribution are modeled by an additive decomposition of different covariate effects.
Boosting distributional copula regression
1 INTRODUCTION The analysis of complex association structures between multiple outcome variables is of increasing interest in contemporary biomedical research. For instance, in genetic epidemiology the joint consideration of multiple phenotypes leads to a better understanding of physical and mental disorders and the identification of relevant genetic risk factors (Ghosh, 2014; Ott & Wang, 2011).
In search of lost edges: a case study on reconstructing financial networks
• In this paper, different network reconstruction methods are compared using a payment network. • The performance of different methods varies strongly, depending on their usage for the reconstruction of binary or valued networks. • There exists no standard solution that is able to reconstruct all properties of a network equally well. • If exogenous information is available it should be used to increase the predictive quality.
In search of lost edges: a case study on reconstructing financial networks
Tweet Facebook LinkedIn Save this article Send to Print this page • In this paper, different network reconstruction methods are compared using a payment network. • The performance of different methods varies strongly, depending on their usage for the reconstruction of binary or valued networks. • There exists no standard solution that is able to reconstruct all properties of a network equally well. • If exogenous information is available it should be used to increase the predictive quality.
Cold War spy satellite images reveal long-term declines of a philopatric keystone species in response to cropland expansion
1. Background Agriculture is essential for human societies, but millennia of agricultural land-use changes have transformed much of the planet's land surface and contributed to the ongoing biodiversity crisis [1–3]. The world's grasslands are particularly affected by agriculture, with as much as 80% lost on some continents [4].
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Nadja
Contact Nadja, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack