18471744. SPLITTING INTEGRATORS FOR FAST SAMPLING FROM DIFFUSION GENERATIVE MODELS (Robert Bosch GmbH)
SPLITTING INTEGRATORS FOR FAST SAMPLING FROM DIFFUSION GENERATIVE MODELS
Organization Name
Inventor(s)
Kushagra Pandey of Irvine CA US
SPLITTING INTEGRATORS FOR FAST SAMPLING FROM DIFFUSION GENERATIVE MODELS
This abstract first appeared for US patent application 18471744 titled 'SPLITTING INTEGRATORS FOR FAST SAMPLING FROM DIFFUSION GENERATIVE MODELS
Original Abstract Submitted
Splitting integrators are provided for fast sampling from a diffusion generative model. A stochastic differential equation (SDE) for the diffusion generative model is split into multiple terms, the multiple terms including deterministic components and random components. Each of the multiple terms is solved to perform a time-reversed noise process using a splitting integrator such that each of the multiple terms is solved separately. Alternating is performed between taking integration steps according to each of the multiple terms. The solving is repeated a desired quantity of steps to complete the time-reversed noise process.