mlsanityData to 14 Oct 2026

Tight Margin-Based Generalization Bounds for Voting Classifiers over Finite Hypothesis Sets

arXiv 2511.20407 ↗First posted 25 Nov 2025cs.LG math.ST stat.THcited by 2

Not on the map. Why?

Abstract (arXiv)

We prove the first margin-based generalization bound for voting classifiers, that is asymptotically tight in the tradeoff between the size of the hypothesis set, the margin, the fraction of training points with the given margin, the number of training samples and the failure probability.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 9 of its 24 references that are in the map. First posted on arXiv 25 Nov 2025.

Builds on

9 of 24 references.

References · 9

  1. 2022Bagging is an Optimal PAC Learnercited by 34
  2. 2022Optimal Weak to Strong Learningcited by 14
  3. 2020Margins are Insufficient for Explaining Gradient Boostingcited by 10
  4. 2019Margin-Based Generalization Lower Bounds for Boosted Classifierscited by 9
  5. 2023AdaBoost is not an Optimal Weak to Strong Learnercited by 6
  6. 2025Improved Margin Generalization Bounds for Voting Classifierscited by 4
  7. 2019Optimal Minimal Margin Maximization with Boostingcited by 3
  8. 2024The Many Faces of Optimal Weak-to-Strong Learningcited by 3
  9. 2025Tight Generalization Bounds for Large-Margin Halfspacescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026A Fine-Grained Understanding of Uniform Convergence for Halfspacescited by 0
  2. 2026Tight Generalization Bound for AdaBoostcited by 0