DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transport.

Zezeng Li Shenghao Li Zhanpeng Wang Na Lei Zhongxuan Luo Xianfeng Gu

Published in: CoRR (2023)

Keyphrases

dynamic programming
data driven
average reward reinforcement learning
generative model
markov decision
bayesian networks
information theoretic
neural network
information retrieval
information systems
website
multiscale
optimal solution
closed form
anisotropic diffusion