paper-with-me

홈 › Papers

How does Lipschitz Regularization Influence GAN Training?

2018-11-23 · ECCV 2020 8 · Yipeng Qin, Niloy Mitra, Peter Wonka

Despite the success of Lipschitz regularization in stabilizing GAN training, the exact reason of its effectiveness remains poorly understood. The direct effect of $K$-Lipschitz regularization is to restrict the $L2$-norm of the neural network gradient to be smaller than a threshold $K$ (e.g., $K=1$) such that $\|\nabla f\| \leq K$. In this work, we uncover an even more important effect of Lipschitz regularization by examining its impact on the loss function: It degenerates GAN loss functions to almost linear ones by restricting their domain and interval of attainable gradient values. Our analysis shows that loss functions are only successful if they are degenerated to almost linear ones. We also show that loss functions perform poorly if they are not degenerated and that a wide range of functions can be used as loss function as long as they are sufficiently degenerated by regularization. Basically, Lipschitz regularization ensures that all loss functions effectively work in the same way. Empirically, we verify our proposition on the MNIST, CIFAR10 and CelebA datasets.

📄 PDF Abstract BibTeX arXiv:1811.09567

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Spectral Normalization Spectral Normalization is a normalization technique used for generative adversarial networks, used to stabilize training of the discriminator. Spectral normalization has the…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Lipschitz regularized Deep Neural Networks generalize and are adversarially robust

2018-08-28 · Chris Finlay, Jeff Calder, Bilal Abbasi, Adam Oberman

In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness. The proof of generalization does n…

Adversarial Robustness

CLIP: Cheap Lipschitz Training of Neural Networks

2021-03-23 · Leon Bungert, René Raab, Tim Roith, Leo Schwinn 외

Despite the large success of deep neural networks (DNN) in recent years, most neural networks still lack mathematical guarantees in terms of stability. For instance, DNNs are vulnerable to small or even imperceptible inp…

Adversarial Lipschitz Regularization

2019-07-12 · ICLR 2020 1 · Dávid Terjék

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 …

Image Generation

Redesigning Regularization for Effective Policy Smoothing

2026-06-11 · Taisuke Kobayashi, Naoto Yamanaka arxiv

This paper proposes a novel regularization design to effectively smooth policy functions in reinforcement learning. While regularization that enhances ``global'' Lipschitz continuity was initially considered, it has been…

Reinforcement Learning

Orthogonal Wasserstein GANs

2019-11-29 · Jan Müller, Reinhard Klein, Michael Weinmann

Wasserstein-GANs have been introduced to address the deficiencies of generative adversarial networks (GANs) regarding the problems of vanishing gradients and mode collapse during the training, leading to improved converg…