gan-ttur-convergence

IN premise — entries/2026/06/21/wiki-Generative_adversarial_network-chunk-3.md

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

The Two Time-Scale Update Rule (TTUR) sets the generator's learning rate lower than the discriminator's and provably converges to a stationary local Nash equilibrium, but does not prevent mode collapse

Dependents

These beliefs depend on this one:

• OUT gan-stable-convergence-guaranteed — GAN training reliably converges to the unique equilibrium where the generator matches the data distribution, given TTUR and asymptotic consistency guarantees.
• 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.