A convenient infinite dimensional framework for generative adversarial learning

HIGHLIGHTS

• who: Hayk Asatryan and colleagues from the School of Mathematics and, University of Wuppertal, Germany have published the research work: A convenient infinite dimensional framework for generative adversarial learning, in the Journal: (JOURNAL)
• what: The authors propose an infinite dimensional theoretical framework for generative adversarial learning. Under these assumptions the authors show that the Rosenblatt transformation induces an optimal generator which is realizable in the hypothesis space of C k u03b1 -generators. While the loss functions used in many works aim at reducing the JensenShannon (JS) divergence between the true distribution and the class of . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.