Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Function Space Particle Optimization for 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 |
|---|---|---|---|
| perform particle optimization in function space rather than weight space | BNNs · MNIST | test error: 1.29% -> 1.21% | Helped |
| perform particle optimization in function space rather than weight space | BNNs · Concrete | test RMSE: 5.32 \pm 0.10 -> 4.31\pm 0.18 | Helped |
| perform particle optimization in function space rather than weight space | BNNs · Mushroom bandit | cumulative regret: Bootstrap $\mathbf{2.71\pm 0.22$; f-SVGD $4.39\pm 0.39$ | Mixed |
| perform particle optimization in function space rather than weight space | BNNs · Wheel bandit | cumulative regret: $42.16\pm 7.80$ -> $\mathbf{7.54\pm 0.41}$ | Helped |
| replace the RBF weight-space kernel with a function-value kernel (ablation) | weight-space SVGD · Boston | test NLL: $2.50\pm 0.03$ -> $2.49\pm 0.06$ | No clear effect |
| replace weight-space particle optimization with function-space particle optimization (ablation) | POVI · synthetic regression | epistemic uncertainty approximation | Helped |
| increase BNN model complexity (ablation) | weight-space POVI · synthetic regression | posterior approximation quality: 5 to 100 hidden units | Hurt |
| increase BNN model complexity (ablation) | function-space POVI · synthetic regression | posterior approximation quality: 5 to 100 hidden units | No clear effect |
Closest papers by meaning
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (ICLR 2024 · similarity 0.89)
- Bayesian Optimization with Robust Bayesian Neural Networks (NeurIPS 2016 · similarity 0.88)
- Bayesian Optimization via Continual Variational Last Layer Training (ICLR 2025 · similarity 0.87)
- Training Bayesian Neural Networks with Sparse Subspace Variational Inference (ICLR 2024 · similarity 0.86)
- Path-Guided Particle-based Sampling (ICML 2024 · similarity 0.86)
- Bayesian Optimization of Function Networks with Partial Evaluations (ICML 2024 · 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.