Year: 2024
Type: preprint
Abstract: Consistency models imitate the multi-step sampling of score-based diffusion in a single forward pass of a neural network. They can be learned in two ways: consistency distillation and consistency training. The former relies on the true velocity field of the corresponding differential equation, approximated by a pre-trained neural network. In contrast, the latter uses a single-sample Monte Carlo estimate of this velocity field. The related estimation error induces a discrepancy between consistency distillation and training that, we show, still holds in the continuous-time limit. To alleviate this issue, we propose a novel flow that transports noisy data towards their corresponding outputs derived from a consistency model. We prove that this flow reduces the previously identified discrepancy and the noise-data transport cost. Consequently, our method not only accelerates consistency training convergence but also enhances its overall performance. The code is available at: https://github.com/thibautissenhuth/consistency_GC.
Source: arXiv (Cornell University)
Authors: Issenhuth, Thibaut, Lee, Sangchul, Santos, Ludovic Dos, Franceschi, Jean-Yves, Kim, Chansoo, Rakotomamonjy, Alain
Institution: Criteo (France)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G4876063428
OpenAlex ID: W4399758697