Mastodawn

Following up on this, I also explored a more direct use of #WassersteinDistance in #WGANs: Instead of training a discriminator, the generator is optimized by explicitly computing the #OptimalTransport distance between real and generated samples. This turns the loss into the actual metric of interest and removes the adversarial setup, leading to a more direct and stable training signal. And we can generate cool animations, too ^_^

🌍 https://www.fabriziomusacchio.com/blog/2023-07-30-wgan_with_direct_wasserstein_distance/

#MachineLearning #Wasserstein

Fabrizio Musacchio Aug 21, 2023

Eliminating the middleman: You can apply the computation of the #Wasserstein distance even more directly in #WassersteinGANs (#WGANs), eliminating the need for a discriminator.

🌎 https://www.fabriziomusacchio.com/blog/2023-07-30-wgan_with_direct_wasserstein_distance/

#MachineLearning

Eliminating the middleman: Direct Wasserstein distance computation in WGANs without discriminator

We explore an alternative approach to implementing WGANs. Contrasting from the standard implementation that requires both a generator and discriminator, the method discussed here employs the optimal transport to compute the Wasserstein distance directly between the real and generated data distributions, eliminating the need for a discriminator.

Fabrizio Musacchio