AI Paper Atlas

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

Flow-Induced Diagonal Gaussian Processes

Moule Lin, Andrea Patane, Weipeng Jing, Shuhao Guan, Goetz Botterweck

AAAI 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Priors and functional variational uncertainty · 1 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
Enlarge inducing matrix from 32x32 to 64x64 (ablation)FiD-GP ResNet-18 · CIFAR-100accuracy: 69.83 -> 73.26Improved
Enlarge inducing matrix from 64x64 to 128x128 (ablation)FiD-GP ResNet-18 · CIFAR-100accuracy: 73.26 -> 76.11Improved
Enlarge inducing matrix from 128x128 to 256x256 (ablation)FiD-GP ResNet-18 · CIFAR-100accuracy: 76.11 -> 77.48Improved
Enlarge inducing matrix from 32x32 to 256x256 (parameter compression lost) (ablation)FiD-GP ResNet-18 · CIFAR-100parameters: 1.35M -> 12.1MHurt
Apply FiD-GP to all layers instead of 4 layers (Matheron) (ablation)FiD-GP ResNet-18 · ImageNet-1kparameters (M): 8.48M -> 5.62MImproved
Apply FiD-GP to all layers instead of 4 layers (Matheron) (ablation)FiD-GP ResNet-18 · ImageNet-1kaccuracy: 70.17 -> 70.19No clear effect
Apply FiD-GP to all layers instead of 4 layers (Matheron) (ablation)FiD-GP ResNet-18 · CIFAR-100accuracy: 76.27 -> 76.11No clear effect
Use Matheron instead of Reparam sampling (4 layers) (ablation)FiD-GP ResNet-18 · ImageNet-1kaccuracy: 70.00 -> 70.17No clear effect
Use Matheron instead of Reparam sampling (4 layers) (ablation)FiD-GP ResNet-18 · CIFAR-100accuracy: 75.99 -> 76.27No clear effect
Use FiD-GP instead of FFG-U for OoD detectionResNet-18 · ImageNet-1k vs SVHNAUROC: 83.7 -> 99.9Improved
Use FiD-GP instead of BatchEnsemble for OoD detectionResNet-18 · ImageNet-1k vs SVHNAUROC: 94.3 -> 99.9Improved
Use FiD-GP (Matheron, 4 layers) instead of BatchEnsemble for segmentation accuracyFCN-ResNet50 · CamVIDmIoU: 63.1 -> 62.8Hurt

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