Timezone: »

 
Let us Build Bridges: Understanding and Extending Diffusion Generative Models
Xingchao Liu · Lemeng Wu · Mao Ye · Qiang Liu

@
in NeurIPS 2022 Workshop on Score-Based Methods »
Event URL: https://openreview.net/forum?id=0ef0CRKC9uZ »

Diffusion-based generative models have achieved promising results recently, but raise an array of open questions in terms of conceptual understanding, theoretical analysis, algorithm improvement and extensions to discrete, structured, non-Euclidean domains. This work tries to re-exam the overall framework, in order to gain better theoretical understandings and develop algorithmic extensions for data from arbitrary domains. By viewing diffusion models as latent variable models with unobserved diffusion trajectories and applying maximum likelihood estimation (MLE) with latent trajectories imputed from an auxiliary distribution, we show that both the model construction and the imputation of latent trajectories amount to constructing diffusion bridge processes that achieve deterministic values and constraints at end point, for which we provide a systematic study and a suit of tools. Leveraging our framework, we present a simple and unified approach to learning on data from different discrete and constrained domains. Experiments show that our methods perform superbly on generating images and semantic segments.

Author Information

Xingchao Liu (University of Texas, Austin)
Lemeng Wu (The University of Texas at Austin)
Mao Ye (The University of Texas at Austin)
Qiang Liu (Dartmouth College)

More from the Same Authors