Extends solvable GAN theory to structured latent covariances, proving convergence of stochastic training to ODEs and identifying a correlation-based signal-boosting mechanism for subspace recovery.
IEEE Journal of Selected Topics in Signal Processing 12:1240--1252
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Effective Covariance Dynamics in Solvable High-Dimensional GANs
Extends solvable GAN theory to structured latent covariances, proving convergence of stochastic training to ODEs and identifying a correlation-based signal-boosting mechanism for subspace recovery.