Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Bootstrapping neural processes
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 |
|---|---|---|---|
| Add bootstrap resampling and bagging to the base neural process | CNP · 1D regression Periodic | target log-likelihood: -1.747 -> -1.082 | Helped |
| Add bootstrap resampling and bagging to the attentive neural process | CANP · EMNIST unseen classes (10-46) | target log-likelihood: 0.834 -> 0.942 | Helped |
| Add bootstrap resampling and bagging to the attentive neural process | CANP · Predator-prey real | target log-likelihood: -8.007 -> -5.465 | Helped |
| Remove paired-bootstrap context resampling (ablation) | BNP · 1D regression Periodic | target log-likelihood: -1.089 -> -1.342 | Hurt |
| Remove the adaptation layer (ablation) | BNP · 1D regression RBF | target log-likelihood: 0.523 -> 0.455 | Hurt |
| Remove the adaptation layer (ablation) | BNP · 1D regression Periodic | target log-likelihood: -1.089 -> -0.845 | Helped |
| Remove the additional base-model loss (ablation) | BNP · 1D regression RBF | target log-likelihood: 0.523 -> 0.496 | Hurt |
Closest papers by meaning
- Martingale Posterior Neural Processes (ICLR 2023 · similarity 0.89)
- Autoregressive Conditional Neural Processes (ICLR 2023 · similarity 0.88)
- Flow Matching Neural Processes (NeurIPS 2025 · similarity 0.87)
- Rényi Neural Processes (ICML 2025 · similarity 0.85)
- Dimension Agnostic Neural Processes (ICLR 2025 · similarity 0.85)
- Dimension-free Score Matching and Time Bootstrapping for Diffusion Models (NeurIPS 2025 · similarity 0.84)
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.