Saved in:
Bibliographic Details
Main Authors: Jain, Nishant, Huang, Xunpeng, Ma, Yian, Zhang, Tong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.01049
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915303058833408
author Jain, Nishant
Huang, Xunpeng
Ma, Yian
Zhang, Tong
author_facet Jain, Nishant
Huang, Xunpeng
Ma, Yian
Zhang, Tong
contents Consistency models have recently emerged as a compelling alternative to traditional SDE-based diffusion models. They offer a significant acceleration in generation by producing high-quality samples in very few steps. Despite their empirical success, a proper theoretic justification for their speed-up is still lacking. In this work, we address the gap by providing a theoretical analysis of consistency models capable of mapping inputs at a given time to arbitrary points along the reverse trajectory. We show that one can achieve a KL divergence of order $ O(\varepsilon^2) $ using only $ O\left(\log\left(\frac{d}{\varepsilon}\right)\right) $ iterations with a constant step size. Additionally, under minimal assumptions on the data distribution (non smooth case) an increasingly common setting in recent diffusion model analyses we show that a similar KL convergence guarantee can be obtained, with the number of steps scaling as $ O\left(d \log\left(\frac{d}{\varepsilon}\right)\right) $. Going further, we also provide a theoretical analysis for estimation of such consistency models, concluding that accurate learning is feasible using small discretization steps, both in smooth and non-smooth settings. Notably, our results for the non-smooth case yield best in class convergence rates compared to existing SDE or ODE based analyses under minimal assumptions.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01049
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Step Consistency Models: Fast Generation with Theoretical Guarantees
Jain, Nishant
Huang, Xunpeng
Ma, Yian
Zhang, Tong
Machine Learning
Analysis of PDEs
Statistics Theory
Consistency models have recently emerged as a compelling alternative to traditional SDE-based diffusion models. They offer a significant acceleration in generation by producing high-quality samples in very few steps. Despite their empirical success, a proper theoretic justification for their speed-up is still lacking. In this work, we address the gap by providing a theoretical analysis of consistency models capable of mapping inputs at a given time to arbitrary points along the reverse trajectory. We show that one can achieve a KL divergence of order $ O(\varepsilon^2) $ using only $ O\left(\log\left(\frac{d}{\varepsilon}\right)\right) $ iterations with a constant step size. Additionally, under minimal assumptions on the data distribution (non smooth case) an increasingly common setting in recent diffusion model analyses we show that a similar KL convergence guarantee can be obtained, with the number of steps scaling as $ O\left(d \log\left(\frac{d}{\varepsilon}\right)\right) $. Going further, we also provide a theoretical analysis for estimation of such consistency models, concluding that accurate learning is feasible using small discretization steps, both in smooth and non-smooth settings. Notably, our results for the non-smooth case yield best in class convergence rates compared to existing SDE or ODE based analyses under minimal assumptions.
title Multi-Step Consistency Models: Fast Generation with Theoretical Guarantees
topic Machine Learning
Analysis of PDEs
Statistics Theory
url https://arxiv.org/abs/2505.01049