mlsanityData to 7 Oct 2026

Self-Bounding Majority Vote Learning Algorithms by the Direct Minimization of a Tight PAC-Bayesian C-Bound

arXiv 2104.13626 ↗First posted 28 Apr 2021stat.ML cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

In the PAC-Bayesian literature, the C-Bound refers to an insightful relation between the risk of a majority vote classifier (under the zero-one loss) and the first two moments of its margin (i.e., the expected margin and the voters' diversity). Until now, learning algorithms developed in this framework minimize the empirical version of the C-Bound, instead of explicit PAC-Bayesian generalization bounds. In this paper, by directly optimizing PAC-Bayesian guarantees on the C-Bound, we derive self-bounding majority vote learning algorithms. Moreover, our algorithms based on gradient descent are scalable and lead to accurate predictors paired with non-vacuous guarantees.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 10 of its 37 references that are in the map. First posted on arXiv 28 Apr 2021.

Builds on

10 of 37 references.

References · 10

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016CVXPY: A Python-Embedded Modeling Language for Convex Optimizationcited by 633
  5. 2017Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Datacited by 527
  6. 2015Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithmcited by 50
  7. 2020Second Order PAC-Bayesian Bounds for the Weighted Majority Votecited by 34
  8. 2019Constrained Deep Networks: Lagrangian Optimization via Log-Barrier Extensionscited by 30
  9. 2018Learning Gaussian Processes by Minimizing PAC-Bayesian Generalization Boundscited by 24
  10. 2018On PAC-Bayesian Bounds for Random Forestscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 1; 2023: 0; 2024: 1; 2025: 2; 2026: 2.

8 papers.

  1. 2021Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Boundcited by 16
  2. 2021Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Votecited by 13
  3. 2022On Margins and Generalisation for Voting Classifierscited by 7
  4. 2025A Framework for Bounding Deterministic Risk with PAC-Bayes: Applications to Majority Votescited by 3
  5. 2026Bound to Disagree: Generalization Bounds via Certifiable Surrogatescited by 2
  6. 2024Multi-View Majority Vote Learning Algorithms: Direct Minimization of PAC-Bayesian Boundscited by 1
  7. 2025Sample Compression for Self Certified Continual Learningcited by 1
  8. 2026On the disintegration of the stochastic majority vote: From PAC-Bayesian bounds to a self-bounding algorithmcited by 0