Research map / Learning theory and algorithms / Prediction and decision losses
Second Order PAC-Bayesian Bounds for the Weighted Majority Vote
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 |
|---|---|---|---|
| Optimize random-forest tree weights using TND rather than FO | Random forests · Test set | majority-vote test loss | Mixed |
| Optimize random-forest tree weights using FO | Random forests · Test set | majority-vote test loss | Hurt |
| Use TND instead of FO for the uniform-weight bound | Random forests · 16 UCI and LibSVM datasets | bound tightness: 5 out of 16 datasets | Mixed |
| Estimate binary-classification disagreements using unlabeled data | Binary second-order bound · Binary classification with considerably more unlabeled than labeled data | risk-bound tightness | Helped |
| Use TND rather than FO to optimize weights | Random-forest ensemble · Test set | weight distribution across trees | Mixed |
Closest papers by meaning
- Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound (NeurIPS 2021 · similarity 0.91)
- PAC-Bayesian Bounds on Rate-Efficient Classifiers (ICML 2022 · similarity 0.90)
- Exact power indices for plurality-voting ensembles (NeurIPS 2026 · similarity 0.85)
- How many classifiers do we need? (NeurIPS 2024 · similarity 0.84)
- Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound (NeurIPS 2024 · similarity 0.83)
- Partition Tree: Conditional Density Estimation over General Outcome Spaces (NeurIPS 2026 · similarity 0.83)
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.