mlsanityData to 14 Oct 2026

Adversarial Lipschitz Regularization

arXiv 1907.05681 ↗First posted 12 Jul 2019cs.LG cs.CV stat.MLcited by 30

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks (GANs) are one of the most popular approaches when it comes to training generative models, among which variants of Wasserstein GANs are considered superior to the standard GAN formulation in terms of learning stability and sample quality. However, Wasserstein GANs require the critic to be 1-Lipschitz, which is often enforced implicitly by penalizing the norm of its gradient, or by globally restricting its Lipschitz constant via weight normalization techniques. Training with a regularization term penalizing the violation of the Lipschitz constraint explicitly, instead of through the norm of the gradient, was found to be practically infeasible in most situations. Inspired by Virtual Adversarial Training, we propose a method called Adversarial Lipschitz Regularization, and show that using an explicit Lipschitz penalty is indeed viable and leads to competitive performance when applied to Wasserstein GANs, highlighting an important connection between Lipschitz regularization and adversarial training.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 5; 2023: 12; 2024: 3; 2025: 0; 2026: 2.

30 papers.

Sort:

By area:

  1. 2023Extracting Training Data from Diffusion Modelscited by 732
  2. 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
  3. 2022Learning Smooth Neural Functions via Lipschitz Regularizationcited by 86
  4. 2022PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Latticescited by 73
  5. 2021CLIP: Cheap Lipschitz Training of Neural Networkscited by 29
  6. 2023Some Fundamental Aspects about Lipschitz Continuity of Neural Networkscited by 26
  7. 2021Gradient Normalization for Generative Adversarial Networkscited by 25
  8. 2023Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariancecited by 19
  9. 2023Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothingcited by 18
  10. 2023Advancing Bayesian Optimization via Learning Correlated Latent Spacecited by 18
  11. 2022A Quantitative Geometric Approach to Neural-Network Smoothnesscited by 16
  12. 2023SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layercited by 14
18 more
  1. 2023Robust low-rank training via approximate orthonormal constraintscited by 13
  2. 2021Analytical bounds on the local Lipschitz constants of ReLU networkscited by 12
  3. 2021Self-Supervised GANs with Label Augmentationcited by 9
  4. 2021Moreau-Yosida f-divergencescited by 5
  5. 2024Accelerate Neural Subspace-Based Reduced-Order Solver of Deformable Simulation by Lipschitz Optimizationcited by 5
  6. 2022GAN-based Domain Inference Attackcited by 4
  7. 2023Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineeringcited by 4
  8. 2024Careful with that Scalpel: Improving Gradient Surgery with an EMAcited by 4
  9. 2023Data Interpolants -- That's What Discriminators in Higher-order Gradient-regularized GANs Arecited by 2
  10. 2021Stein Latent Optimization for Generative Adversarial Networkscited by 1
  11. 2022On Deep Learning in Password Guessing, a Surveycited by 1
  12. 2026Variation Brownian Kernel Ladderscited by 1
  13. 2021Variational Autoencoders: A Harmonic Perspectivecited by 0
  14. 2023Lamarr: LHCb ultra-fast simulation based on machine learning models deployed within Gausscited by 0
  15. 2023Penalty Gradient Normalization for Generative Adversarial Networkscited by 0
  16. 2023Stability Analysis Framework for Particle-based Distance GANs with Wasserstein Gradient Flowcited by 0
  17. 2024DataFreeShield: Defending Adversarial Attacks without Training Datacited by 0
  18. 2026Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent Dynamicscited by 0