StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow
Researchers have developed a new method called StAD to improve the speed and accuracy of likelihood calculations in diffusion and flow-based generative models. This technique bypasses the need to compute the Jacobian of the probability flow ODE, instead learning the divergence directly using the Langevin-Stein operator. StAD has demonstrated competitive performance against existing methods like Hutchinson and Hutch++ on various density estimation tasks, showing improved variance and speed. AI
IMPACT Accelerates likelihood computation for diffusion and flow-based models, benefiting Bayesian analysis and density estimation tasks.