Potential Flow Generator With L2 Optimal Transport Regularity for Generative Models

We propose a potential flow generator with L₂ optimal transport regularity, which can be easily integrated into a wide range of generative models, including different versions of generative adversarial networks (GANs) and normalizing flow models. With only a slight augmentation to the original generator loss functions, our generator not only tries to transport the input distribution to the target one but also aims to find the one with minimum L₂ transport cost. We show the effectiveness of our method in several 2-D problems and illustrate the concept of ``proximity'' due to the L₂ optimal transport regularity. Subsequently, we demonstrate the effectiveness of the potential flow generator in image translation tasks with unpaired training data from the MNIST data set and the CelebA data set with a comparison against vanilla Wasserstein GAN with gradient penalty (WGAN-GP) and CycleGAN.

[1]  Yann Brenier,et al.  A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem , 2000, Numerische Mathematik.

[2]  Paris Perdikaris,et al.  Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations , 2017, ArXiv.

[3]  Caroline Uhler,et al.  Scalable Unbalanced Optimal Transport using Generative Adversarial Networks , 2018, ICLR.

[4]  Alexander G. Schwing,et al.  Generative Modeling Using the Sliced Wasserstein Distance , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[5]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[6]  W. Gangbo,et al.  The geometry of optimal transportation , 1996 .

[7]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[8]  Ping Tan,et al.  DualGAN: Unsupervised Dual Learning for Image-to-Image Translation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[9]  Aaron C. Courville,et al.  Adversarial Computation of Optimal Transport Maps , 2019, ArXiv.

[10]  Paris Perdikaris,et al.  Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations , 2017, ArXiv.

[11]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[12]  Nestor Guillen,et al.  Five lectures on optimal transportation: Geometry, regularity and applications , 2010, 1011.2911.

[13]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[14]  Hyunsoo Kim,et al.  Learning to Discover Cross-Domain Relations with Generative Adversarial Networks , 2017, ICML.

[15]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

[16]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[17]  Han Zhang,et al.  Improving GANs Using Optimal Transport , 2018, ICLR.

[18]  L. Ambrosio,et al.  Gradient Flows: In Metric Spaces and in the Space of Probability Measures , 2005 .

[19]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Felix Otto,et al.  Viscous Fingering: An Optimal Bound on the Growth Rate of the Mixing Zone , 1997, SIAM J. Appl. Math..

[21]  Nicolas Courty,et al.  Large Scale Optimal Transport and Mapping Estimation , 2017, ICLR.

[22]  Shakir Mohamed,et al.  Variational Inference with Normalizing Flows , 2015, ICML.

[23]  Prafulla Dhariwal,et al.  Glow: Generative Flow with Invertible 1x1 Convolutions , 2018, NeurIPS.

[24]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[25]  Xiaogang Wang,et al.  Deep Learning Face Attributes in the Wild , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[26]  David Duvenaud,et al.  Neural Ordinary Differential Equations , 2018, NeurIPS.

[27]  M. Gelbrich.  On a Formula for the L2 Wasserstein Metric between Measures on Euclidean and Hilbert Spaces , 1990 .

[28]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.