A Sharp KL-Convergence Analysis for Diffusion Models under Minimal Assumptions
By: Nishant Jain, Tong Zhang
Potential Business Impact:
Makes AI create better pictures, faster.
Diffusion-based generative models have emerged as highly effective methods for synthesizing high-quality samples. Recent works have focused on analyzing the convergence of their generation process with minimal assumptions, either through reverse SDEs or Probability Flow ODEs. The best known guarantees, without any smoothness assumptions, for the KL divergence so far achieve a linear dependence on the data dimension $d$ and an inverse quadratic dependence on $\varepsilon$. In this work, we present a refined analysis that improves the dependence on $\varepsilon$. We model the generation process as a composition of two steps: a reverse ODE step, followed by a smaller noising step along the forward process. This design leverages the fact that the ODE step enables control in Wasserstein-type error, which can then be converted into a KL divergence bound via noise addition, leading to a better dependence on the discretization step size. We further provide a novel analysis to achieve the linear $d$-dependence for the error due to discretizing this Probability Flow ODE in absence of any smoothness assumptions. We show that $\tilde{O}\left(\tfrac{d\log^{3/2}(\frac{1}{\delta})}{\varepsilon}\right)$ steps suffice to approximate the target distribution corrupted with Gaussian noise of variance $\delta$ within $O(\varepsilon^2)$ in KL divergence, improving upon the previous best result, requiring $\tilde{O}\left(\tfrac{d\log^2(\frac{1}{\delta})}{\varepsilon^2}\right)$ steps.
Similar Papers
Fast Convergence for High-Order ODE Solvers in Diffusion Probabilistic Models
Machine Learning (CS)
Makes AI create realistic pictures faster and better.
Multi-Step Consistency Models: Fast Generation with Theoretical Guarantees
Machine Learning (CS)
Makes AI create pictures much faster.
The Effect of Stochasticity in Score-Based Diffusion Sampling: a KL Divergence Analysis
Machine Learning (CS)
Makes AI art generation more accurate and controllable.