Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
The Ridgelet Prior: A Covariance Function Approach to Prior Specification for Bayesian Neural Networks
Takuo Matsubara, Chris J. Oates, François-Xavier Briol
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 changed | Where | Measured | Effect |
|---|---|---|---|
| increase number of hidden units N from 100 to 3000 in ridgelet-prior BNN (ablation) | Ridgelet prior BNN · GP approximation, squared exponential kernel, d=1 | MRMSE to target GP | Improved |
| use ridgelet prior instead of i.i.d. prior | BNN with 500 hidden units · Mauna Loa CO2 prediction | similarity of posterior predictive to GP posterior | Improved |
| use ridgelet prior instead of i.i.d. prior | BNN with 2000 hidden units · In-painting task | qualitative reconstruction of missing region | Improved |
| increase network depth from L=1 to L=5 hidden layers with 10,000 units each (ablation) | Ridgelet prior BNN · GP approximation | MMD^2 to target GP | Hurt |
Closest papers by meaning
- Exact marginal prior distributions of finite Bayesian neural networks (NeurIPS 2021 · similarity 0.89)
- Bayesian Optimization via Continual Variational Last Layer Training (ICLR 2025 · similarity 0.88)
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (ICLR 2024 · similarity 0.86)
- FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning (NeurIPS 2024 · similarity 0.86)
- Critical feature learning in deep neural networks (ICML 2024 · similarity 0.86)
- Bayesian Low-Rank Learning (Bella): A Practical Approach to Bayesian Neural Networks (AAAI 2025 · 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.
