AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

The surrogate Gibbs-posterior of a corrected stochastic MALA: Towards uncertainty quantification for neural networks

Sebastian Bieringer, Gregor Kasieczka, Maximilian F. Steffen, Mathias Trabs

JMLR 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Approximate inference in Bayesian neural networks

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the correction term to the stochastic Metropolis-Hastings risk (csMALA vs sMALA)stochastic MALA · 1D regression, 10401-parameter ReLU netvalidation riskImproved
use full-sample MH step (MALA) instead of corrected stochastic MHcsMALA · 1D regression, moderate batch probabilityvalidation riskNo clear effect
add the correction term to stochastic MHsMALA · 1D regression, varying batch probabilityacceptance rateImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy