Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learning
Veit David Wild, Robert Hu, Dino Sejdinovic
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use a DNN variational mean with the SVGP covariance instead of the SVGP mean and covariance | GWI · UCI regression datasets | mean rank: 5.5 -> 2.06 | Improved |
| Use GWI-net rather than the strongest listed baseline | image classification models · Fashion MNIST | accuracy: 91.60$\pm$0.14 -> 93.25 $\pm$0.09 | Improved |
| Use GWI-net rather than the strongest listed baseline | image classification models · Fashion MNIST | NLL: 0.254$\pm$0.05 -> 0.250 $\pm$0.00 | Improved |
| Use GWI-net rather than the strongest listed baseline | image classification models · Fashion MNIST | OOD-AUC: 0.956 $\pm$0.06 -> 0.959 $\pm$0.01 | No clear effect |
| Use GWI-net rather than the strongest listed baseline | image classification models · CIFAR-10 | accuracy: 77.69 $\pm$0.64 -> 83.82 $\pm$0.00 | Improved |
| Use GWI-net rather than the strongest listed baseline | image classification models · CIFAR-10 | NLL: 0.661$\pm$0.00 -> 0.553 $\pm$0.00 | Improved |
| Use GWI-net rather than the strongest listed baseline | image classification models · CIFAR-10 | OOD-AUC: 0.883 $\pm$0.04 -> 0.618 $\pm$0.00 | Hurt |
Closest papers by meaning
- Variational inference via Gaussian interacting particles in the Bures-Wasserstein geometry (ICML 2026 · similarity 0.89)
- Forward-Backward Gaussian Variational Inference via JKO in the Bures-Wasserstein Space (ICML 2023 · similarity 0.89)
- Variational inference via Wasserstein gradient flows (NeurIPS 2022 · similarity 0.88)
- Scalable Uncertainty for Computer Vision With Functional Variational Inference (CVPR 2020 · similarity 0.88)
- Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold (ICLR 2025 · similarity 0.88)
- VIKING: Deep variational inference with stochastic projections (NeurIPS 2025 · similarity 0.86)
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.
