Johanna Menn

Papers

Total Citations

H-Index

About

Johanna Menn is a rising researcher in the field of safe machine learning, with a core focus on Bayesian optimization under safety constraints—a critical area for high-stakes applications like robotics and biomedical engineering. Her most-cited work, "On Safety in Safe Bayesian Optimization" (2024), tackles the fundamental challenge of optimizing unknown functions while guaranteeing that all evaluated points remain within safe operational limits. This paper addresses a pressing gap: despite the growing use of safe Bayesian optimization in practice, theoretical foundations for ensuring safety were often lacking. Menn’s contribution lies in rigorously formalizing these safety guarantees, providing a framework that balances exploration with strict constraint satisfaction. Though early in her career, her work has already garnered attention (3 citations in its first year), signaling its relevance to a community urgently seeking reliable methods for autonomous systems. By bridging theory and application, Menn is helping to build the mathematical backbone for deploying AI in environments where failure is not an option—from robotic surgery to autonomous driving. Her research promises to shape how future engineers design algorithms that are both efficient and provably safe.