arXiv subjects

Peter Kuhn

Publications and source records attributed to Peter Kuhn.

5 recordsLinked to original sources

arXiv2026

Artificial Empathy: Towards a Framework for Unsupervised Agency Detection and Policy Reconstruction

We study how an AI system can identify and model other agents in its environment from observation alone, which is a capability necessary for cooperative behaviour in the real world. This problem is less constrained than inverse reinforcement learning and remains largely unexplored. We propose a framework that uses a reinforcement learning agent, trained on an independent task as a prior about agentic dynamics, to perform agency detection and policy reconstruction.

cs.AI↗

arXiv2026

Distribution-Aware Conformal Prediction: A Framework for generating efficient prediction intervals for time series

We present Distribution-aware Conformal Prediction (DCP), a unified framework integrating probabilistic predictors like Monte Carlo dropout, deep ensembles, and quantile regression with score-agnostic conformal calibration to produce valid and efficient prediction intervals. Leveraging a numerical inversion approach to construct interval bounds, DCP accommodates arbitrary combinations of distribution generating predictors and nonconformity scores. Benchmark analysis on synthetic and real-world time series data demonstrate DCP's ability to adaptively calibrate prediction intervals under varying uncertainty regimes. Crucially, DCP's modular design facilitates plug-and-play experimentation with different predictor-score pairings, quantitatively supported by a newly introduced modified Winkler score that balances validity and efficiency by explicitly penalizing undercoverage. While DCP generalizes and extends existing approaches like Conformalized Quantile Regression and Conformalized Monte Carlo, its modular design allows further extensions, setting a foundation for advancing uncertainty quantification in dynamic environments and high-risk applications.

cs.LG↗

arXiv2022

Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach

Federated Learning (FL) is a novel paradigm for the shared training of models based on decentralized and private data. With respect to ethical guidelines, FL is promising regarding privacy, but needs to excel vis-à-vis transparency and trustworthiness. In particular, FL has to address the accountability of the parties involved and their adherence to rules, law and principles. We introduce AF^2 Framework, where we instrument FL with accountability by fusing verifiable claims with tamper-evident facts, into reproducible arguments. We build on AI FactSheets for instilling transparency and trustworthiness into the AI lifecycle and expand it to incorporate dynamic and nested facts, as well as complex model compositions in FL. Based on our approach, an auditor can validate, reproduce and certify a FL process. This can be directly applied in practice to address the challenges of AI engineering and ethics.

cs.AI↗

arXiv2011

Die Maxwellgleichung mit wechselnden Randbedingungen (The Maxwell Equation with Mixed Boundary Conditions)

In the thesis at hand we give a comprehensive discussion of basic problems for generalized Maxwell equations with mixed boundary conditions using the calculus of alternating differential forms on Riemannian manifolds of arbitrary dimension. We prove compactness results, Hodge decompositions and Poincare type estimates. For the case of 'full' boundary conditions we present trace and extension theorems, regularity theory as well as a detailed solution theory for static Maxwell problems.

math.AP↗

arXiv2011

Regularity Results for Generalized Electro-Magnetic Problems

We prove regularity results up to the boundary for time independent generalized Maxwell equations on Riemannian manifolds with boundary using the calculus of alternating differential forms. We discuss homogeneous and inhomogeneous boundary data and show 'polynomially weighted' regularity in exterior domains as well.

math.AP↗