Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
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 |
|---|---|---|---|
| Apply repriorisation before underdamped LMC | FCN · CIFAR-10, n=256, width 1024 | per-step ESS: 50x | Helped |
| Apply repriorisation before underdamped LMC | FCN · CIFAR-10, n=1024, 10240, 40960, width 1024 | per-step ESS: around 10x | Helped |
| Apply repriorisation before underdamped LMC | Wide ResNet-20 · CIFAR-10, n=1K | per-step ESS: more than 10x | Helped |
| Apply repriorisation before underdamped LMC | Wide ResNet-20 · CIFAR-10, n=10K | per-step ESS | No clear effect |
| Increase network width while keeping dataset size fixed | Repriorised FCN · CIFAR-10, n=256 | per-step ESS speedup over standard parametrisation: 50x | Helped |
| Set regularisation parameter λ to σ² rather than tuning it | Repriorised FCN · CIFAR-10, tested widths | per-step ESS | Helped |
Closest papers by meaning
- Reparameterization invariance in approximate Bayesian inference (NeurIPS 2024 · similarity 0.89)
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (ICLR 2024 · similarity 0.89)
- Reparameterized Importance Sampling for Robust Variational Bayesian Neural Networks (ICML 2024 · similarity 0.89)
- A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors (ICLR 2024 · similarity 0.87)
- Parameter Expanded Stochastic Gradient Markov Chain Monte Carlo (ICLR 2025 · similarity 0.87)
- Posterior Contraction Rates for sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces (NeurIPS 2026 · 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.