5 papers
Prediction-powered Neural Architecture Search
Pascal Janetzky, Yuxin Wang, Michael Klar +1
Evaluating candidate architectures in neural architecture search (NAS) faces an inherent trade-off: on the one hand, reliable performance labels are limited because training and ev…
Continual Learning of Domain-Invariant Representations
Pascal Janetzky, Tobias Schlagenhauf, Stefan Feuerriegel
Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain…
ORTHOBO: Orthogonal Bayesian Hyperparameter Optimization
Maresa Schröder, Pascal Janetzky, Michael Klar +1
Bayesian optimization is widely used for hyperparameter optimization when model evaluations are expensive; however, noisy acquisition estimates can lead to unstable decisions. We i…
MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questions
Hui Min Wong, Philip Heesen, Pascal Janetzky +2
Large language models (LLMs) are increasingly used for diagnostic tasks in medicine. In clinical practice, the correct diagnosis can rarely be immediately inferred from the initial…
Slowing Down Forgetting in Continual Learning
Pascal Janetzky, Tobias Schlagenhauf, Stefan Feuerriegel
A common challenge in continual learning (CL) is catastrophic forgetting, where the performance on old tasks drops after new, additional tasks are learned. In this paper, we propos…