6 papers
On Hyperparameter Tuning on the Test Set
Matteo Fregonara, Tom Viering, Jan van Gemert
"Don't tune hyperparameters on the test set" is often stated in machine learning textbooks. Violating it is considered a cardinal sin that produces misleadingly optimistic results,…
MalTree: Tracing Malware Evolution from Embeddings at Scale
Akash Amalan, Georgios Smaragdakis, Tom J. Viering
Malware detection remains largely reactive: machine learning models trained on known samples degrade as threats evolve. Understanding evolutionary relationships among malware famil…
-PFN: Fast Entropy Search via In-Context Learning
Herilalaina Rakotoarison, Steven Adriaensen, Tom Viering +4
Information-theoretic acquisition functions such as Entropy Search (ES) offer a principled exploration-exploitation framework for Bayesian optimization (BO). However, their practic…
Transformers can do Bayesian Clustering
Prajit Bhaskaran, Tom Viering
Bayesian clustering accounts for uncertainty but is computationally demanding at scale. Furthermore, real-world datasets often contain missing values, and simple imputation ignores…
LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought
Cheng Yan, Felix Mohr, Tom Viering
Sample-wise learning curves plot performance versus training set size. They are useful for studying scaling laws and speeding up hyperparameter tuning and model selection. Learning…
The Unreasonable Effectiveness Of Early Discarding After One Epoch In Neural Network Hyperparameter Optimization
Romain Egele, Felix Mohr, Tom Viering +1
To reach high performance with deep learning, hyperparameter optimization (HPO) is essential. This process is usually time-consuming due to costly evaluations of neural networks. E…