Directly Fine-Tuning Diffusion Models on Differentiable Rewards.

Kevin Clark Paul Vicol Kevin Swersky David J. Fleet

Published in: CoRR (2023)

Keyphrases

fine tuning
diffusion models
diffusion model
viable alternative
fine tune
information diffusion
fine tuned
social networks
reinforcement learning
dynamic programming
random walk
objective function
user behavior
influence maximization