English

Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projection

Computer Vision and Pattern Recognition 2026-04-07 v1

Abstract

This paper presents a novel framework to accelerate score-based diffusion models. It first converts the standard stable diffusion model into the Fokker-Planck formulation which results in solving large linear systems for each image. For training involving many images, it can lead to a high computational cost. The core innovation is a cross-matrix Krylov projection method that exploits mathematical similarities between matrices, using a shared subspace built from ``seed" matrices to rapidly solve for subsequent ``target" matrices. Our experiments show that this technique achieves a 15.8\% to 43.7\% time reduction over standard sparse solvers. Additionally, we compare our method against DDPM baselines in denoising tasks, showing a speedup of up to 115×\times. Furthermore, under a fixed computational budget, our model is able to produce high-quality images while DDPM fails to generate recognizable content, illustrating our approach is a practical method for efficient generation in resource-limited settings.

Keywords

Cite

@article{arxiv.2511.17634,
  title  = {Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projection},
  author = {Kaikwan Lau and Andrew S. Na and Justin W. L. Wan},
  journal= {arXiv preprint arXiv:2511.17634},
  year   = {2026}
}
R2 v1 2026-07-01T07:49:31.235Z