2 papers
cs.LG2026
Gaussian Neural Networks
Peter Kuhn, Victoria Heusinger-Heß
Gaussian neural networks (GaNNs) are proposed as a novel regularization mechanism for neural networks. From a Bayesian perspective standard regularization techniques can be viewed…
cs.LG2026
Distribution-Aware Conformal Prediction: A Framework for generating efficient prediction intervals for time series
Daniel Schweizer, Peter Kuhn, Jayant Sharma +3
We present Distribution-aware Conformal Prediction (DCP), a unified framework integrating probabilistic predictors like Monte Carlo dropout, deep ensembles, and quantile regression…