HPO, PhD Student
Johannes Hog

Postal address
Institut für InformatikAlbert-Ludwigs-Universität Freiburg
Sekretariat Hutter/Maschinelles Lernen
Georges-Köhler-Allee 074
79110 Freiburg, Germany
Office
Building 074, Room 00-012I am a PhD student at the University of Freiburg, supervised by Prof. Frank Hutter as part of the Small Data Initiative. My research focuses on improving the efficiency of scaling law estimation for (tabular) foundation models, with a particular interest in multi-fidelity hyperparameter optimization using Prior-data Fitted Networks.
I finished my Masters at the University of Freiburg in 2023. During my Master's, I participated in two AutoML competitions, which focused on AutoML for diverse tasks. I ranked third in the AutoML Decathlon competition and ranked first in all three phases (phase 1, phase 2, phase 3) of the follow-up AutoML Cup competition.
Publications
2025 |
nanoTabPFN: A Lightweight and Educational Reimplementation of TabPFN Workshop 2025. |
Meta-learning Population-based Methods for Reinforcement Learning Journal Article In: Transactions on Machine Learning Research, 2025, ISBN: 2835-8856. |
2024 |
Warmstarting for Scaling Language Models Inproceedings In: NeurIPS 2024 Workshop Adaptive Foundation Models, 2024. |
2022 |
AutoML Decathlon: Diverse Tasks, Modern Methods, and Efficiency at Scale Inproceedings In: Ciccone, Marco; Stolovitzky, Gustavo; Albrecht, Jacob (Ed.): Proceedings of the NeurIPS 2022 Competitions Track, pp. 151–170, PMLR, 2022. |