Time-varying generative models are guided by natural gradient descent through a time-score projection onto an exponential-family manifold, yielding kernel-based particle update algorithms KiNG and ntKiNG.
Wasserstein generative adversarial networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Guiding Time-Varying Generative Models with Natural Gradients on Exponential Family Manifold
Time-varying generative models are guided by natural gradient descent through a time-score projection onto an exponential-family manifold, yielding kernel-based particle update algorithms KiNG and ntKiNG.