Research map / Learning theory and algorithms / Sample complexity
Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote
Yi-Shan Wu, Andres R Masegosa, Stephan Sloth Lorenzen, Christian Igel, Yevgeny Seldin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 weights with Chebyshev-Cantelli bound using PAC-Bayes-Bennett loss estimate (CCPBB) instead of tandem bound (TND) | weighted random forest · UCI/LibSVM binary and multiclass datasets | test loss ratio vs uniform weighting | Improved |
| use CCPBB bound instead of TND bound as the guarantee | weighted random forest · UCI/LibSVM datasets | bound tightness ratio to TND | Hurt |
| use CCTND bound instead of TND bound | heterogeneous classifier ensembles · UCI/LibSVM datasets | bound tightness ratio to TND | Improved |
| optimize weights by first order bound (FO) instead of uniform weighting | heterogeneous classifier ensembles · UCI/LibSVM datasets | test loss ratio vs uniform weighting | Mixed |
| optimize weights by TND, CCTND or CCPBB instead of uniform weighting | heterogeneous classifier ensembles · UCI/LibSVM datasets | test loss ratio vs uniform weighting | Improved |
Closest papers by meaning
- Erratum: Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithm (JMLR 2023 · similarity 0.88)
- PAC-Bayes Un-Expected Bernstein Inequality (NeurIPS 2019 · similarity 0.87)
- PAC-Bayes-Chernoff bounds for unbounded losses (NeurIPS 2024 · similarity 0.85)
- Tight Bounds on the Distortion of Randomized and Deterministic Distributed Voting (NeurIPS 2025 · similarity 0.83)
- Intrinsic-dimension empirical Bernstein inequalities for bounded self-adjoint operators (NeurIPS 2026 · similarity 0.83)
- Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound (NeurIPS 2024 · 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.
