mlsanityData to 7 Oct 2026

Near-Tight Margin-Based Generalization Bounds for Support Vector Machines

arXiv 2006.02175 ↗First posted 3 Jun 2020cs.LG stat.MLcited by 19

Not on the map. Why?

Abstract (arXiv)

Support Vector Machines (SVMs) are among the most fundamental tools for binary classification. In its simplest formulation, an SVM produces a hyperplane separating two classes of data using the largest possible margin to the data. The focus on maximizing the margin has been well motivated through numerous generalization bounds. In this paper, we revisit and improve the classic generalization bounds in terms of margins. Furthermore, we complement our new generalization bound by a nearly matching lower bound, thus almost settling the generalization performance of SVMs in terms of margins.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 2; 2024: 4; 2025: 5; 2026: 2.

19 papers.

Sort:

By area:

  1. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 108
  2. 2024Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiencycited by 34
  3. 2021On Margins and Derandomisation in PAC-Bayescited by 19
  4. 2023Machine Unlearning: A Surveycited by 18
  5. 2022Optimal Weak to Strong Learningcited by 14
  6. 2022Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learningcited by 14
  7. 2024Let Go of Your Labels with Unsupervised Transfercited by 14
  8. 2024Weisfeiler-Leman at the margin: When more expressivity matterscited by 13
  9. 2024Replicable Learning of Large-Margin Halfspacescited by 12
  10. 2023Lessons from Generalization Error Analysis of Federated Learning: You May Communicate Less Often!cited by 8
  11. 2025WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatchcited by 4
  12. 2025Sample Selection via Contrastive Fragmentation for Noisy Label Regressioncited by 4
7 more
  1. 2025Borsuk-Ulam and Replicable Learning of Large-Margin Halfspacescited by 3
  2. 2025Tight Generalization Bounds for Large-Margin Halfspacescited by 1
  3. 2025Heterogeneity Matters even More in Distributed Learning: Study from Generalization Perspectivecited by 1
  4. 2021Compression Implies Generalizationcited by 0
  5. 2022On the Optimization of Margin Distributioncited by 0
  6. 2026A Fine-Grained Understanding of Uniform Convergence for Halfspacescited by 0
  7. 2026Information-Theoretic Analysis of Next-Token Prediction under Markovian Datacited by 0