On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow

Youssef Mroueh, Truyen Nguyen
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:1720-1728, 2021.

Abstract

We consider the maximum mean discrepancy MMD GAN problem and propose a parametric kernelized gradient flow that mimics the min-max game in gradient regularized MMD GAN. We show that this flow provides a descent direction minimizing the MMD on a statistical manifold of probability distributions. We then derive an explicit condition which ensures that gradient descent on the parameter space of the generator in gradient regularized MMD GAN is globally convergent to the target distribution. Under this condition , we give non asymptotic convergence results for MMD GAN. Another contribution of this paper is the introduction of a dynamic formulation of a regularization of MMD and demonstrating that the parametric kernelized descent for MMD is the gradient flow of this functional with respect to the new Riemannian structure. Our obtained theoretical result allows ones to treat gradient flows for quite general functionals and thus has potential applications to other types of variational inferences on a statistical manifold beyond GANs. Finally, numerical experiments suggest that our parametric kernelized gradient flow stabilizes GAN training and guarantees convergence.

Cite this Paper


BibTeX
@InProceedings{pmlr-v130-mroueh21a, title = { On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow }, author = {Mroueh, Youssef and Nguyen, Truyen}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {1720--1728}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/mroueh21a/mroueh21a.pdf}, url = {https://proceedings.mlr.press/v130/mroueh21a.html}, abstract = { We consider the maximum mean discrepancy MMD GAN problem and propose a parametric kernelized gradient flow that mimics the min-max game in gradient regularized MMD GAN. We show that this flow provides a descent direction minimizing the MMD on a statistical manifold of probability distributions. We then derive an explicit condition which ensures that gradient descent on the parameter space of the generator in gradient regularized MMD GAN is globally convergent to the target distribution. Under this condition , we give non asymptotic convergence results for MMD GAN. Another contribution of this paper is the introduction of a dynamic formulation of a regularization of MMD and demonstrating that the parametric kernelized descent for MMD is the gradient flow of this functional with respect to the new Riemannian structure. Our obtained theoretical result allows ones to treat gradient flows for quite general functionals and thus has potential applications to other types of variational inferences on a statistical manifold beyond GANs. Finally, numerical experiments suggest that our parametric kernelized gradient flow stabilizes GAN training and guarantees convergence. } }
Endnote
%0 Conference Paper %T On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow %A Youssef Mroueh %A Truyen Nguyen %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-mroueh21a %I PMLR %P 1720--1728 %U https://proceedings.mlr.press/v130/mroueh21a.html %V 130 %X We consider the maximum mean discrepancy MMD GAN problem and propose a parametric kernelized gradient flow that mimics the min-max game in gradient regularized MMD GAN. We show that this flow provides a descent direction minimizing the MMD on a statistical manifold of probability distributions. We then derive an explicit condition which ensures that gradient descent on the parameter space of the generator in gradient regularized MMD GAN is globally convergent to the target distribution. Under this condition , we give non asymptotic convergence results for MMD GAN. Another contribution of this paper is the introduction of a dynamic formulation of a regularization of MMD and demonstrating that the parametric kernelized descent for MMD is the gradient flow of this functional with respect to the new Riemannian structure. Our obtained theoretical result allows ones to treat gradient flows for quite general functionals and thus has potential applications to other types of variational inferences on a statistical manifold beyond GANs. Finally, numerical experiments suggest that our parametric kernelized gradient flow stabilizes GAN training and guarantees convergence.
APA
Mroueh, Y. & Nguyen, T.. (2021). On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:1720-1728 Available from https://proceedings.mlr.press/v130/mroueh21a.html.

Related Material