Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Asymptotic Properties for Bayesian Neural Network in Besov Space
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 spike-and-slab prior on network parameters | Bayesian ReLU network · Besov-space regression with known smoothness | posterior contraction rate: n^{-s/(2s+d)}(\log n)^{3/2} | Helped |
| Put a prior on network architecture to adapt to unknown smoothness | Bayesian ReLU network with spike-and-slab prior · Besov-space regression with unknown smoothness | posterior contraction rate: n^{-s/(2s+d)}(\log n)^{3/2} | Helped |
| Replace spike-and-slab with a shrinkage prior satisfying the stated mass and tail conditions | Bayesian ReLU network · Besov-space regression | posterior contraction rate: \epsilon_n = n^{-s/(2s+d)}(\log n)^{3/2} | Helped |
| Use the Gaussian shrinkage prior with the specified scale | Bayesian ReLU network · Besov-space regression | posterior contraction rate | Helped |
Closest papers by meaning
- Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality (NeurIPS 2025 · similarity 0.93)
- Posterior Contraction Rates for sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces (NeurIPS 2026 · similarity 0.89)
- Exact marginal prior distributions of finite Bayesian neural networks (NeurIPS 2021 · similarity 0.88)
- Training Bayesian Neural Networks with Sparse Subspace Variational Inference (ICLR 2024 · similarity 0.87)
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (ICLR 2024 · similarity 0.86)
- Scalable Bayesian Learning with posteriors (ICLR 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.