Score-based generative diffusion with "active" correlated noise sources
Alexandra Lamtyugina, Agnish Kumar Behera, Aditya Nandy, Carlos Floyd, Suriyanarayanan Vaikuntanathan
11/11/2024
cs.LGcond-mat.dis-nn
No confident code implementation found for this paper. 1 possible match can be shown below.
Abstract
Diffusion models exhibit robust generative properties by approximating the underlying distribution of a dataset and synthesizing data by sampling from the approximated distribution. In this work, we explore how the generative performance may be be modulated if noise sources with temporal correlations -- akin to those used in the field of active matter -- are used for the destruction of the data in the forward process. Our numerical and analytical experiments suggest that the corresponding reverse process may exhibit improved generative properties.
