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. My Ph.D. position is part of the Small Data Initiative, where I work on project B01: Transfer- and meta-learning in deep networks for human brain-signal analysis. I'm particularly interested in Hyperparameter Optimization and Meta-learning.

I finished my Masters at the University of Freiburg in 2023. During my Masters 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

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.