← Back to all news
arXiv Machine Learning By Daniel Zhengyu Huang, Jiaoyang Huang, Zhengjiang Lin

Fast Convergence for High-Order ODE Solvers in Diffusion Probabilistic Models

Read the original on arXiv Machine Learning →

arXiv:2506. 13061v4 Announce Type: replace Abstract: Diffusion probabilistic models generate samples by learning to reverse a noise-injection process that transforms data into noise.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Statistics ML
Aug 25

Provably adaptive sampling with uniform and remasking discrete diffusion models

The paper proves that for discrete diffusion models using uniform or remasking forward processes, an adaptive sampler based on a leave‑one‑out denoiser can achieve sampling error proportional to the score‑estimation error plus a small tolerance. The required number of discretization steps scales with the dual total correlation of the target distribution, not directly with the ambient dimension. This result shows that sampling complexity is governed by the intrinsic dependence structure of the distribution, and the authors provide an information‑theoretic analysis linking discretization error to mutual information between coordinates.

By Daniil Dmitriev, Zhihan Huang, Yuting Wei
diffusion
More like this →
arXiv Machine Learning
Jul 17

The Effect of Stochasticity in Score-Based Diffusion Sampling: a KL Divergence Analysis

arXiv:2506. 11378v3 Announce Type: replace Abstract: Sampling in score-based diffusion models can be performed by solving either a reverse-time stochastic differential equation (SDE) parameterized by an arbitrary stochasticity function or a probability flow ODE, corresponding to setting this stochasticity function to zero.

By Bernardo P. Schaeffer, Ricardo M. S. Rosa, Glauco Valle
diffusionbenchmarks
More like this →
arXiv Statistics ML
Oct 5

KL Convergence Guarantees for Score diffusion models under minimal data assumptions

The paper presents new Kullback–Leibler convergence guarantees for score diffusion models that avoid restrictive Lipschitz assumptions on the score function. By analyzing models with fixed step size derived from the Ornstein–Uhlenbeck semigroup and its kinetic counterpart, the authors derive simple, sharp KL bounds that hold for any data distribution with finite Fisher information relative to the standard Gaussian. This extends theoretical guarantees to a broader class of data distributions without requiring early stopping or compact support.

By Giovanni Conforti, Alain Durmus, Marta Gentiloni Silveri
diffusion
More like this →