all AI news
On the Nash equilibrium of moment-matching GANs for stationary Gaussian processes. (arXiv:2203.07136v2 [stat.ML] UPDATED)
July 6, 2022, 1:11 a.m. | Sixin Zhang
stat.ML updates on arXiv.org arxiv.org
Generative Adversarial Networks (GANs) learn an implicit generative model
from data samples through a two-player game. In this paper, we study the
existence of Nash equilibrium of the game which is consistent as the number of
data samples grows to infinity. In a realizable setting where the goal is to
estimate the ground-truth generator of a stationary Gaussian process, we show
that the existence of consistent Nash equilibrium depends crucially on the
choice of the discriminator family. The discriminator defined …
arxiv equilibrium gans gaussian processes ml nash equilibrium processes
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote