mlsanityData to 7 Oct 2026

PAC-Bayesian Generalization Bounds for Adversarial Generative Models

arXiv 2302.08942 ↗First posted 17 Feb 2023cs.LG cs.AI stat.MLcited by 13

Not on the map. Why?

Abstract (arXiv)

We extend PAC-Bayesian theory to generative models and develop generalization bounds for models based on the Wasserstein distance and the total variation distance. Our first result on the Wasserstein distance assumes the instance space is bounded, while our second result takes advantage of dimensionality reduction. Our results naturally apply to Wasserstein GANs and Energy-Based GANs, and our bounds provide new training objectives for these two. Although our work is mainly theoretical, we perform numerical experiments showing non-vacuous generalization bounds for Wasserstein GANs on synthetic datasets.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 45 of its 74 references that are in the map. First posted on arXiv 17 Feb 2023.

Builds on

45 of 74 references.

References · 45

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  8. 2017A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networkscited by 309
  9. 2021The Intrinsic Dimension of Images and Its Impact on Learningcited by 307
  10. 2015A note on the evaluation of generative modelscited by 291
  11. 2018GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classificationcited by 242
  12. 2021User-friendly introduction to PAC-Bayes boundscited by 234
33 more
  1. 2018Pros and Cons of GAN Evaluation Measurescited by 224
  2. 2019Uniform convergence may be unable to explain generalization in deep learningcited by 223
  3. 2016Adversarially Learned Inferencecited by 216
  4. 2018Sorting out Lipschitz function approximationcited by 211
  5. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
  6. 2018Low-Shot Learning from Imaginary Datacited by 181
  7. 2017Generalization and Equilibrium in Generative Adversarial Nets (GANs)cited by 165
  8. 2019A Primer on PAC-Bayesian Learningcited by 130
  9. 2020Tighter risk certificates for neural networkscited by 112
  10. 2016PAC-Bayesian Theory Meets Bayesian Inferencecited by 87
  11. 2017Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priorscited by 81
  12. 2018How Well Generative Adversarial Networks Learn Distributionscited by 78
  13. 2017Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theorycited by 76
  14. 2020Distributional Sliced-Wasserstein and Applications to Generative Modelingcited by 69
  15. 2020PAC-Bayes Analysis Beyond the Usual Boundscited by 63
  16. 2017On the Discrimination-Generalization Tradeoff in GANscited by 48
  17. 2020Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixturescited by 47
  18. 2020PAC-Bayes unleashed: generalisation bounds with unbounded lossescited by 43
  19. 2018Towards High Resolution Video Generation with Progressive Growing of Sliced Wasserstein GANscited by 36
  20. 2020Some Theoretical Insights into Wasserstein GANscited by 28
  21. 2020Statistical guarantees for generative models without dominationcited by 27
  22. 2018Nonparametric Density Estimation under Adversarial Lossescited by 26
  23. 2019Prescribed Generative Adversarial Networkscited by 23
  24. 2019Nonparametric Density Estimation & Convergence Rates for GANs under Besov IPM Lossescited by 22
  25. 2022Online PAC-Bayes Learningcited by 22
  26. 2022On PAC-Bayesian reconstruction guarantees for VAEscited by 20
  27. 2021On Margins and Derandomisation in PAC-Bayescited by 19
  28. 2022Integral Probability Metrics PAC-Bayes Boundscited by 19
  29. 2018Consistency of Variational Bayes Inference for Estimation and Model Selection in Mixturescited by 17
  30. 2022A survey on text generation using generative adversarial networkscited by 16
  31. 2019Improved PAC-Bayesian Bounds for Linear Regressioncited by 12
  32. 2022Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distancescited by 7
  33. 2021On Predicting Generalization using GANscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 3; 2025: 2; 2026: 4.

13 papers.

Sort:

By area:

  1. 2024Mission Impossible: A Statistical Perspective on Jailbreaking LLMscited by 21
  2. 2024Position: Understanding LLMs Requires More Than Statistical Generalizationcited by 20
  3. 2023Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theorycited by 16
  4. 2023Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-artcited by 14
  5. 2023Wasserstein PAC-Bayes Learning: Exploiting Optimisation Guarantees to Explain Generalisationcited by 3
  6. 2023Information-Theoretic Generalization Bounds for Transductive Learning and its Applicationscited by 2
  7. 2025Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysiscited by 2
  8. 2026Bound to Disagree: Generalization Bounds via Certifiable Surrogatescited by 2
  9. 2026PAC-Bayesian Reconstruction Guarantees for Time Series Variational Autoencoderscited by 1
  10. 2024How Learning Dynamics Drive Adversarially Robust Generalization?cited by 0
  11. 2025Deep Actor-Critics with Tight Risk Certificatescited by 0
  12. 2026Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesiscited by 0
1 more
  1. 2026Proof-of-Authorship for Diffusion-based AI Generated Contentcited by 0