Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Asymptotics of representation learning in finite 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 |
|---|---|---|---|
| increase hidden layer width n in a deep linear fully-connected BNN | deep linear BNN, 2 hidden layers · MNIST (5000 images), Langevin sampling | Frobenius deviation of average kernel from GP kernel | Helped |
| increase channel width in a deep linear 2-D convolutional BNN | deep linear CNN BNN · MNIST (50 images) | norm of correction to GP kernel | Helped |
| insert a narrow bottleneck layer in an otherwise wide ReLU BNN (ablation) | 3-hidden-layer ReLU BNN · MNIST (1000 images) | kernel deviation from GP (representation learning) | Helped |
| increase width of layers around a fixed bottleneck (ablation) | 3-hidden-layer ReLU BNN with bottleneck · MNIST (1000 images) | kernel deviation from GP | Mixed |
Closest papers by meaning
- Critical feature learning in deep neural networks (ICML 2024 · similarity 0.90)
- Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks (NeurIPS 2026 · similarity 0.88)
- Asymptotics of Learning with Deep Structured (Random) Features (ICML 2024 · similarity 0.88)
- Asymptotics of feature learning in two-layer networks after one gradient-step (ICML 2024 · similarity 0.87)
- A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors (ICLR 2024 · similarity 0.86)
- Adaptive kernel predictors from feature-learning infinite limits of neural networks (ICML 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.