gan-non-saturating-loss-original-paper

IN premise — entries/2026/06/21/wiki-Generative_adversarial_network-chunk-4.md

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

The non-saturating generator loss (L_G = E[ln D(x)]) was recommended in the original GAN paper for faster convergence, addressing vanishing gradients when the generator is poor

Dependents

These beliefs depend on this one:

• IN gan-training-stability-requires-multiple-interventions — GAN training stability benefits from several complementary design choices — non-saturating loss to address vanishing gradients when the generator is poor, two-timescale update rule for provable convergence to a stationary local Nash equilibrium (though not mode collapse prevention), and deterministic discriminators for optimality of the discriminator — each addressing a distinct failure mode, but none individually sufficient for overall stability.