TY - GEN
T1 - Reverse-time diffusion processes in discrete time
AU - Dasgupta, Soura
AU - Anderson, Brian D. O.
N1 - © 2025 IEEE
PY - 2025/12
Y1 - 2025/12
N2 - Generative AI relies on finding reverse models for linear discrete time forward diffusions with non-Gaussian initial states, but uses indirect methods for reversal as there is no theory for direct reversal in discrete time. We give sufficient conditions that guarantee the existence of a reverse time diffusion and give a method of meeting them. We also give a necessary and sufficient condition for the reverse model to be input-affine.
AB - Generative AI relies on finding reverse models for linear discrete time forward diffusions with non-Gaussian initial states, but uses indirect methods for reversal as there is no theory for direct reversal in discrete time. We give sufficient conditions that guarantee the existence of a reverse time diffusion and give a method of meeting them. We also give a necessary and sufficient condition for the reverse model to be input-affine.
UR - https://www.scopus.com/pages/publications/105031906012
U2 - 10.1109/CDC57313.2025.11312217
DO - 10.1109/CDC57313.2025.11312217
M3 - Conference Paper
SN - 979-8-3315-2628-3
T3 - Proceedings of the IEEE Conference on Decision and Control
SP - 5487
EP - 5492
BT - 2025 IEEE 64th Conference on Decision and Control, CDC 2025
PB - IEEE
CY - Rio de Janeiro, Brazil
T2 - 64th IEEE Conference on Decision and Control, CDC 2025
Y2 - 9 December 2025 through 12 December 2025
ER -