gan-minimizes-jensen-shannon-divergence

IN premise — entries/2026/06/21/wiki-Generative_adversarial_network-chunk-2.md

Created 2026-06-21T09:55:49+00:00

The original GAN implicitly minimizes the Jensen-Shannon divergence (not KL divergence) between the generated and real data distributions

Dependents

These beliefs depend on this one:

• IN gan-complete-theoretical-characterization — GAN theory provides a complete analytical characterization of optimal behavior: the optimal discriminator has a closed-form solution (Radon-Nikodym derivative), the objective implicitly minimizes Jensen-Shannon divergence, and at the unique equilibrium the generator exactly recovers the data distribution.