Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions
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 a single latent-space density to derive evidence and update a conjugate posterior | NatPN · CIFAR-10 OODom | OODom Alea.: 85.89 ± 4.10 -> 93.67 ± 3.03 | Helped |
| Use NatPN's input-dependent Bayesian update instead of EvReg | Regression · Concrete Compressive Strength | RMSE: 6.04 ± 0.18 -> 5.83 ± 0.23 | Helped |
| Use NatPN's input-dependent Bayesian update instead of EvReg | Regression · NYU Depth v2 | RMSE: 28.88 -> 29.72 | Hurt |
| Use NatPN's Poisson target distribution rather than a Normal target distribution | Bike Sharing · Bike Sharing | Calibration: 1.95 ± 0.34 -> 31.04 ± 1.81 | Hurt |
| Combine multiple NatPN predictions as a Bayesian ensemble | NatPN · Classification | accuracy and calibration | Helped |
| Use one normalizing flow rather than one flow per class | NatPN compared with PostNet · CIFAR-10 | inference time (ms): 88.56 ± 0.06 -> 75.64 ± 0.04 | Helped |
| Estimate uncertainty in one forward pass rather than using five-pass dropout | NatPN compared with Dropout · CIFAR-10 | inference time (ms): 407.91 ± 5.65 -> 75.64 ± 0.04 | Helped |
Closest papers by meaning
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (NeurIPS 2017 · similarity 0.88)
- Natural-Parameter Networks: A Class of Probabilistic Neural Networks (NeurIPS 2016 · similarity 0.88)
- Adaptive Uncertainty Estimation via High-Dimensional Testing on Latent Representations (NeurIPS 2023 · similarity 0.88)
- Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows (NeurIPS 2025 · similarity 0.87)
- Neural Conditional Probability for Uncertainty Quantification (NeurIPS 2024 · similarity 0.86)
- Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models (CVPR 2024 · 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.