EasyDeepLearn

What does WGAN + gradient penalty change vs vanilla GAN?

hard

Answer

  • WGAN uses the Wasserstein distance approximation: max⁡D\operatorname{max}_{D} E[D(x)] - E[D(G(z))] where D (the 'critic') must be 1-Lipschitz.
  • Original WGAN clipped weights (crude).
  • WGAN-GP (Gulrajani 2017) enforces Lipschitz softly with a gradient penalty λ  ⋅  (∣∣∇x  D(x)∣∣2  −  1)2{\lambda}\; \cdot \;( \mid \mid \nabla x\;D(x) \mid \mid _{2}\; - \;1)^{2} on interpolated points x̂.
  • Result: stable training, meaningful loss curve (correlated with sample quality), fewer mode-collapse issues.
Check yourself — multiple choice
  • Same as vanilla GAN
  • Wasserstein loss + gradient penalty enforcing 1-Lipschitz D → stable training, meaningful loss, fewer collapses
  • Removes discriminator
  • Only works for text

WGAN-GP: Wasserstein loss + gradient penalty → stable training + meaningful loss.

#gan#generative#losses

Practise Deep Learning

214 interview questions in this topic.

Read the lessonFlashcardsTake the quiz

Related questions