Higher-order Langevin dynamics reduce memorization in diffusion models by making the data dynamics follow a low-pass-filtered score whose smoothness grows with model order.
arXiv preprint arXiv:2305.14712 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
A PDE framework using Li-Yau inequalities proves well-posedness and sharp stability for score-based Fokker-Planck dynamics, with reverse-time trajectories concentrating on compactly supported data manifolds at rate sqrt(t).
citing papers explorer
-
Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics
Higher-order Langevin dynamics reduce memorization in diffusion models by making the data dynamics follow a low-pass-filtered score whose smoothness grows with model order.
-
The two clocks and the innovation window: When and how generative models learn rules
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
-
A PDE Perspective on Generative Diffusion Models
A PDE framework using Li-Yau inequalities proves well-posedness and sharp stability for score-based Fokker-Planck dynamics, with reverse-time trajectories concentrating on compactly supported data manifolds at rate sqrt(t).