Proves that the squared discrete transportation distance between nearby measures on a connected graph is bounded by the quadratic form of a reweighted Laplacian pseudoinverse, yielding a resistance distance with multiple characterizations and showing the random walk as gradient flow on the resulting
Improving GANs Using Optimal Transport
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution. This metric, which we call mini-batch energy distance, combines optimal transport in primal form with an energy distance defined in an adversarially learned feature space, resulting in a highly discriminative distance function with unbiased mini-batch gradients. Experimentally we show OT-GAN to be highly stable when trained with large mini-batches, and we present state-of-the-art results on several popular benchmark problems for image generation.
verdicts
UNVERDICTED 2representative citing papers
A GAN with Wasserstein discriminator objective makes the generator follow the W2 geodesic to learn an optimal transport map.
citing papers explorer
-
Resistance Distance and Linearized Optimal Transport on Graphs
Proves that the squared discrete transportation distance between nearby measures on a connected graph is bounded by the quadratic form of a reweighted Laplacian pseudoinverse, yielding a resistance distance with multiple characterizations and showing the random walk as gradient flow on the resulting
-
Adversarial Computation of Optimal Transport Maps
A GAN with Wasserstein discriminator objective makes the generator follow the W2 geodesic to learn an optimal transport map.