AI Paper Atlas

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

Bayesian Deep Learning via Subnetwork Inference

Erik Daxberger, Eric Nalisnick, James U Allingham, Javier Antoran, Jose Miguel Hernandez-Lobato

ICML 2021 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Approximate inference in Bayesian neural networks · 10 citations (OpenAlex)

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
Use Wasserstein-selected rather than uniformly random subnetwork weights (ablation)Subnetwork Linearized Laplace · MNIST vs FashionMNISTAUC-ROC: 0.75 ± 0.02 -> 0.92 ± 0.05Improved
Use Wasserstein-selected rather than uniformly random subnetwork weights (ablation)Subnetwork Linearized Laplace · CIFAR10 vs SVHNAUC-ROC: 0.86 ± 0.02 -> 0.85 ± 0.03No clear effect
Use Wasserstein-selected rather than uniformly random subnetwork weights (ablation)Subnetwork Linearized Laplace · MNIST, 45° rotationlog-likelihood: -1.60 \scriptstyle \pm 0.05 -> -1.09 \scriptstyle \pm 0.03Improved
Use Wasserstein-selected rather than uniformly random subnetwork weights (ablation)Subnetwork Linearized Laplace · MNIST, 60° rotationlog-likelihood: -3.85 \scriptstyle \pm 0.18 -> -2.10 \scriptstyle \pm 0.03Improved
Use subnetwork inference instead of VOGNResNet-18 image classification · MNIST, 45° rotationlog-likelihood: -1.15 \scriptstyle \pm nan -> -1.09 \scriptstyle \pm 0.03Improved
Use subnetwork inference instead of VOGNResNet-18 image classification · MNIST, 60° rotationlog-likelihood: -1.92 \scriptstyle \pm nan -> -2.10 \scriptstyle \pm 0.03Hurt

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