On the Existence of Optimal Transport Gradient for Learning Generative Models
arXiv:2102.05542
Abstract
The use of optimal transport cost for learning generative models has become popular with Wasserstein Generative Adversarial Networks (WGAN). Training of WGAN relies on a theoretical background: the calculation of the gradient of the optimal transport cost with respect to the generative model parameters. We first demonstrate that such gradient may not be defined, which can result in numerical instabilities during gradient-based optimization. We address this issue by stating a valid differentiation theorem in the case of entropic regularized transport and specify conditions under which existence is ensured. By exploiting the discrete nature of empirical data, we formulate the gradient in a semi-discrete setting and propose an algorithm for the optimization of the generative model parameters. Finally, we illustrate numerically the advantage of the proposed framework.
References in corpus (12)
- Auto-Encoding Variational Bayes
- Spectral Normalization for Generative Adversarial Networks
- Fast Computation of Wasserstein Barycenters
- Input Convex Neural Networks
- Stochastic Optimization for Large-scale Optimal Transport
- On the regularization of Wasserstein GANs
- Interpolating between Optimal Transport and MMD using Sinkhorn Divergences
- Differentiable Augmentation for Data-Efficient GAN Training
- On the Convergence and Robustness of Training GANs with Regularized Optimal Transport
- Wasserstein-2 Generative Networks
- A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributions
- Debiased Sinkhorn barycenters