Research map / Learning theory and algorithms / Sample complexity
Robust Learning of Fixed-Structure Bayesian 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 |
|---|---|---|---|
| Use spectral filtering to remove suspected corrupted samples rather than estimate conditional probabilities directly from noisy samples | Fixed-structure Bayesian network learning · Synthetic random tree and random graph | estimated total variation distance | Helped |
| Use spectral filtering instead of RANSAC subsampling | Fixed-structure Bayesian network learning · Synthetic random tree and random graph | estimated total variation distance | Helped |
| Use spectral filtering rather than noisy empirical conditional means | ALARM semi-synthetic learning · ALARM | estimated total variation distance | Helped |
| Use spectral filtering instead of RANSAC subsampling | ALARM semi-synthetic learning · ALARM | estimated total variation distance | Helped |
| Increase the corrupted-sample fraction | Filtering on ALARM · ALARM | estimated total variation distance | Hurt |
| Apply filtering when the balancedness assumption on conditional probabilities is violated | Fixed-structure Bayesian network learning · Synthetic data and ALARM | estimated total variation distance | Helped |
Closest papers by meaning
- Robust Learning of Fixed-Structure Bayesian Networks in Nearly-Linear Time (ICLR 2021 · similarity 0.97)
- Distributionally Robust Skeleton Learning of Discrete Bayesian Networks (NeurIPS 2023 · similarity 0.91)
- Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity (NeurIPS 2017 · similarity 0.89)
- Robust Bayesian Neural Networks by Spectral Expectation Bound Regularization (CVPR 2021 · similarity 0.88)
- Adaptive Robust Learning using Latent Bernoulli Variables (ICML 2024 · similarity 0.86)
- Probably Approximately Global Robustness Certification (ICML 2025 · 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.