Menu

HPO, PhD Student

Johannes Hog

Postal address

Institut für Informatik
Albert-Ludwigs-Universität Freiburg
Sekretariat Hutter/Maschinelles Lernen
Georges-Köhler-Allee 074
79110 Freiburg, Germany

Office

Building 074, Room 00-012

I 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

Pfefferle, Alexander; Hog, Johannes; Purucker, Lennart; Hutter, Frank

nanoTabPFN: A Lightweight and Educational Reimplementation of TabPFN Workshop

2025.

Hog, Johannes; Rajan, Raghu; Biedenkapp, André; Awad, Noor; Hutter, Frank; Nguyen, Vu

Meta-learning Population-based Methods for Reinforcement Learning Journal Article

In: Transactions on Machine Learning Research, 2025, ISBN: 2835-8856.

2024

Mallik, Neeratyoy; Janowski, Maciej; Hog, Johannes; Rakotoarison, Herilalaina; Klein, Aaron; Grabocka, Josif; Hutter, Frank

Warmstarting for Scaling Language Models Inproceedings

In: NeurIPS 2024 Workshop Adaptive Foundation Models, 2024.

2022

Roberts, Nicholas; Guo, Samuel; Xu, Cong; Talwalkar, Ameet; Lander, David; Tao, Lvfang; Cai, Linhang; Niu, Shuaicheng; Heng, Jianyu; Qin, Hongyang; Deng, Minwen; Hog, Johannes; Pfefferle, Alexander; Shivakumar, Sushil Ammanaghatta; Krishnakumar, Arjun; Wang, Yubo; Sukthanker, Rhea; Hutter, Frank; Hasanaj, Euxhen; Le, Tien-Dung; Khodak, Mikhail; Nevmyvaka, Yuriy; Rasul, Kashif; Sala, Frederic; Schneider, Anderson; Shen, Junhong; Sparks, Evan

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.