On safety in safe Bayesian optimization

C Fiedler, J Menn, L Kreisköther, S Trimpe - arxiv preprint arxiv …, 2024 - arxiv.org
Optimizing an unknown function under safety constraints is a central task in robotics,
biomedical engineering, and many other disciplines, and increasingly safe Bayesian …

Orthogonal representation learning for estimating causal quantities

V Melnychuk, D Frauen, J Schweisthal… - arxiv preprint arxiv …, 2025 - arxiv.org
Representation learning is widely used for estimating causal quantities (eg, the conditional
average treatment effect) from observational data. While existing representation learning …

On statistical learning theory for distributional inputs

C Fiedler, PF Massiani, F Solowjow… - Forty-first International …, 2024 - openreview.net
Kernel-based statistical learning on distributional inputs appears in many relevant
applications, from medical diagnostics to causal inference, and poses intriguing theoretical …

Recent kernel methods for interacting particle systems: first numerical results

C Fiedler, M Herty, C Segala, S Trimpe - European Journal of …, 2024 - cambridge.org
Interacting particle systems (IPSs) are a very important class of dynamical systems, arising in
different domains like biology, physics, sociology and engineering. In many applications …

Safe exploration in reproducing kernel Hilbert spaces

A Tokmak, KG Krishnan, TB Schön… - ICML 2024 Workshop … - openreview.net
Popular safe Bayesian optimization (BO) algorithms successfully control safety-critical
systems in unknown environments. However, most algorithms require smoothness …