3 papers
cs.LG2026
Scale Sensitivity in Low-Bit Post-Training Quantization: Curvature of the Quantization Error Landscape
Jonas von Berg, Massimiliano Datres, Carlo Kneißl +1
Post-training quantization (PTQ) methods in the GPTQ family minimize a layer-wise reconstruction error on a uniform grid whose scale must be chosen; the common max-based choice deg…
cs.LG2026
The Price of Robustness: Stable Classifiers Need Overparameterization
Jonas von Berg, Adalbert Fono, Massimiliano Datres +2
The relationship between overparameterization, stability, and generalization remains incompletely understood in the setting of discontinuous classifiers. We address this gap by est…
cs.LG2025
Graph Neural Networks for Enhancing Ensemble Forecasts of Extreme Rainfall
Christopher Bülte, Sohir Maskey, Philipp Scholl +2
Climate change is increasing the occurrence of extreme precipitation events, threatening infrastructure, agriculture, and public safety. Ensemble prediction systems provide probabi…