Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Assumed Density Filtering Methods for Learning 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 PBP instead of EBP | Bayesian neural network ADF · UCI regression | test RMSE: 3.87 -> 2.65 | Helped |
| use PBP instead of EBP | Bayesian neural network ADF · UCI regression | predictive log likelihood: −2.11 -> −1.34 | Helped |
| use PBP instead of EBP | Bayesian neural network ADF · binary classification | test error %: 0.27 -> 0.07 | Helped |
| use PBP instead of EBP | Bayesian neural network ADF · toy multiclass posterior | pointwise KL divergence: 0.084 -> 0.074 | Helped |
| use ADF methods (PBP/EBP) instead of standard backprop | neural network · toy multiclass posterior | pointwise KL divergence: 0.783 -> 0.074 | Helped |
| use Poisson count regression instead of Gaussian regression with rounding | PBP · bike rental demand | test log likelihood: −5.12 -> −3.2108 | Helped |
| use stochastic approximation instead of log bound for multiclass (ablation) | EBP/PBP · multiclass | accuracy | Helped |
| use EBP/PBP instead of Cheng et al. 2015 method | Bayesian neural network · MNIST | test error | Helped |
| use PBP/EBP instead of Bayes by backprop (Blundell 2015) | Bayesian neural network · MNIST | test error | No clear effect |
Closest papers by meaning
- Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods (NeurIPS 2020 · similarity 0.87)
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (ICLR 2024 · similarity 0.86)
- A Metalearned Neural Circuit for Nonparametric Bayesian Inference (NeurIPS 2024 · similarity 0.86)
- Do Bayesian Neural Networks Actually Behave Like Bayesian Models? (ICML 2025 · similarity 0.85)
- Martingale Posterior Neural Networks for Fast Sequential Decision Making (NeurIPS 2025 · similarity 0.85)
- Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks (AAAI 2025 · similarity 0.85)
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.