Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Rethinking Likelihood distributions: Student's t Likelihood Boosts Bayesian Neural Network Performance
Pei-Hsuan Hsia, Lars H. Heyen, Arvid Weyrauch +4
In Bayesian neural networks (BNNs), variational inference is a widely adopted framework for modeling uncertainty in a distributional way, with the evidence lower bound (ELBO) servi…
cs.LG2026
PurSAMERE: Reliable Adversarial Purification via Sharpness-Aware Minimization of Expected Reconstruction Error
Vinh Hoang, Sebastian Krumscheid, Holger Rauhut +1
We propose a novel deterministic purification method to improve adversarial robustness by mapping a potentially adversarial sample toward a nearby sample that lies close to a mode…
cs.LG2021
Machine learning-based conditional mean filter: a generalization of the ensemble Kalman filter for nonlinear data assimilation
Truong-Vinh Hoang, Sebastian Krumscheid, Hermann G. Matthies +1
This paper presents the machine learning-based ensemble conditional mean filter (ML-EnCMF) -- a filtering method based on the conditional mean filter (CMF) previously introduced in…