Adaptive Discretization for Consistency Models
This work addresses a bottleneck in training efficiency for CMs, which are used for one-step generation in machine learning, though it is incremental as it builds on existing CM methods.
The paper tackles the inefficiency of manually designed discretization schemes in Consistency Models (CMs) by proposing an adaptive framework that optimizes discretization steps, resulting in significantly improved training efficiency and superior generative performance on CIFAR-10 and ImageNet with minimal overhead.
Consistency Models (CMs) have shown promise for efficient one-step generation. However, most existing CMs rely on manually designed discretization schemes, which can cause repeated adjustments for different noise schedules and datasets. To address this, we propose a unified framework for the automatic and adaptive discretization of CMs, formulating it as an optimization problem with respect to the discretization step. Concretely, during the consistency training process, we propose using local consistency as the optimization objective to ensure trainability by avoiding excessive discretization, and taking global consistency as a constraint to ensure stability by controlling the denoising error in the training target. We establish the trade-off between local and global consistency with a Lagrange multiplier. Building on this framework, we achieve adaptive discretization for CMs using the Gauss-Newton method. We refer to our approach as ADCMs. Experiments demonstrate that ADCMs significantly improve the training efficiency of CMs, achieving superior generative performance with minimal training overhead on both CIFAR-10 and ImageNet. Moreover, ADCMs exhibit strong adaptability to more advanced DM variants. Code is available at https://github.com/rainstonee/ADCM.