Characteristic Learning for Provable One Step Generation

arXiv:2405.05512v1 Announce Type: new
Abstract: We propose the characteristic generator, a novel one-step generative model that combines the efficiency of sampling in Generative Adversarial Networks (GANs) with the stable performance of flow-based models. Our model is driven by characteristics, along which the probability density transport can be described by ordinary differential equations (ODEs). Specifically, We estimate the velocity field through nonparametric regression and utilize Euler method to solve the probability flow ODE, generating a series of discrete approximations to the …

abstract adversarial arxiv cs.ai cs.lg cs.na differential efficiency flow gans generative generative adversarial networks generator math.na math.st networks novel ordinary performance probability sampling stat.th transport type