08.10.2025
Three MCML Members Win Best Paper Award at AutoML 2025
Our Members Matthias Feurer, Lennart Schneider and Bernd Bischl Honored for Their Work on Hyperparameter Optimization
We are happy to announce that the paper “Overtuning in Hyperparameter Optimization” by MCML Thomas Bayes Fellow Matthias Feurer, MCML Junior Member Lennart Schneider, and MCML Director Bernd Bischl has won the Best Paper Award at the 4th AutoML Conference.
The paper defines and studies overtuning, where hyperparameter optimization can improve validation scores but hurt generalization, and presents a large-scale analysis of factors influencing this effect. These insights will help the AutoML community design more robust and reliable optimization strategies
Congratulations to the team on this outstanding achievement!
Check out the full paper:
Overtuning in Hyperparameter Optimization.
Methods Track @AutoML 2025 - Methods Track at the International Conference on Automated Machine Learning. New York City, NY, USA, Sep 08-11, 2025. Best Paper Award. To be published. URL
Related
05.02.2026
Needle in a Haystack: Finding Exact Moments in Long Videos
ECCV 2024 research introduces RGNet, an AI model that finds exact moments in long videos using unified retrieval and grounding.
04.02.2026
Benjamin Busam Leads Design of Bavarian Earth Observation Satellite Network “CuBy”
Benjamin Busam leads the scientific design of the “CuBy” satellite network, delivering AI-ready Earth observation data for Bavaria.
©Florian Generotzky / LMU
30.01.2026
Cracks in the Foundations of Cosmology
Daniel Grün examines cosmological tensions that challenge the Standard Model and may point toward new physics.
