Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Tractable Function-Space Variational Inference in Bayesian Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 KMNIST rather than random monochrome images as context data (ablation) | FSVI on FashionMNIST · FashionMNIST vs MNIST | AUROC: 96.23 -> 99.80 | Helped |
| use KMNIST rather than random monochrome images as context data (ablation) | FSVI on FashionMNIST · FashionMNIST vs NotMNIST | AUROC: 95.02 -> 97.26 | Helped |
| use KMNIST rather than random monochrome images as context data (ablation) | FSVI on FashionMNIST · FashionMNIST test | accuracy: 93.13\pms{0.13} -> 93.48\pms{0.12} | Helped |
| use CIFAR-100 rather than random monochrome images as context data (ablation) | FSVI on CIFAR-10 · CIFAR-10 vs SVHN | AUROC: 94.76 -> 98.07 | Helped |
| use CIFAR-100 rather than random monochrome images as context data (ablation) | FSVI on CIFAR-10 · CIFAR-10 test | ECE: 0.034\pms{0.001} -> 0.026\pms{0.001} | Helped |
| use CIFAR-100 rather than random monochrome images as context data (ablation) | FSVI on CIFAR-10 · Corrupted CIFAR-10 | accuracy: 80.81\pms{0.43} -> 81.20\pms{0.42} | Helped |
Closest papers by meaning
- Deterministic Variational Inference for Robust Bayesian Neural Networks (ICLR 2019 · similarity 0.90)
- FUNCTIONAL VARIATIONAL BAYESIAN NEURAL NETWORKS (ICLR 2019 · similarity 0.90)
- Training Bayesian Neural Networks with Sparse Subspace Variational Inference (ICLR 2024 · similarity 0.88)
- Variational Bayesian Last Layers (ICLR 2024 · similarity 0.87)
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (ICLR 2024 · similarity 0.87)
- VIKING: Deep variational inference with stochastic projections (NeurIPS 2025 · similarity 0.87)
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.