mlsanityData to 7 Oct 2026

A General Framework for the Practical Disintegration of PAC-Bayesian Bounds

arXiv 2102.08649 ↗First posted 17 Feb 2021stat.ML cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

PAC-Bayesian bounds are known to be tight and informative when studying the generalization ability of randomized classifiers. However, they require a loose and costly derandomization step when applied to some families of deterministic models such as neural networks. As an alternative to this step, we introduce new PAC-Bayesian generalization bounds that have the originality to provide disintegrated bounds, i.e., they give guarantees over one single hypothesis instead of the usual averaged analysis. Our bounds are easily optimizable and can be used to design learning algorithms. We illustrate this behavior on neural networks, and we show a significant practical improvement over the state-of-the-art framework.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 2 of its 12 references that are in the map. First posted on arXiv 17 Feb 2021.

Builds on

2 of 12 references.

References · 2

  1. 2020Differentiable PAC-Bayes Objectives with Partially Aggregated Neural Networkscited by 29
  2. 2017PAC-Bayes and Domain Adaptationcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 0; 2023: 4; 2024: 6; 2025: 6; 2026: 3.

21 papers.

Sort:

  1. 2021Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Boundcited by 16
  2. 2024A PAC-Bayesian Link Between Generalisation and Flat Minimacited by 13
  3. 2023Data-dependent Generalization Bounds via Variable-Size Compressibilitycited by 9
  4. 2024Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Setscited by 9
  5. 2024Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measurescited by 7
  6. 2023PAC-Bayes Generalization Certificates for Learned Inductive Conformal Predictioncited by 6
  7. 2023From Mutual Information to Expected Dynamics: New Generalization Bounds for Heavy-Tailed SGDcited by 4
  8. 2024Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworkscited by 3
  9. 2025A Framework for Bounding Deterministic Risk with PAC-Bayes: Applications to Majority Votescited by 3
  10. 2024Tighter Generalisation Bounds via Interpolationcited by 2
  11. 2025Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained modelscited by 2
  12. 2021Kernel Interpolation as a Bayes Point Machinecited by 1
9 more
  1. 2023Practicality of generalization guarantees for unsupervised domain adaptation with neural networkscited by 1
  2. 2024Multi-View Majority Vote Learning Algorithms: Direct Minimization of PAC-Bayesian Boundscited by 1
  3. 2025Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Datacited by 1
  4. 2025Some theoretical improvements on the tightness of PAC-Bayes risk certificates for neural networkscited by 1
  5. 2025PAC-Bayesian Bounds on Constrained f-Entropic Risk Measurescited by 1
  6. 2026Smoothness-Based Derandomization of PAC-Bayes Boundscited by 1
  7. 2025Generalization of the Gibbs algorithm with high probability at low temperaturescited by 0
  8. 2026PAC-Bayesian Generalization Guarantees for Fairness on Stochastic and Deterministic Classifierscited by 0
  9. 2026On the disintegration of the stochastic majority vote: From PAC-Bayesian bounds to a self-bounding algorithmcited by 0