|国家预印本平台
首页|Efficiently Access Diffusion Fisher: Within the Outer Product Span Space

Efficiently Access Diffusion Fisher: Within the Outer Product Span Space

Efficiently Access Diffusion Fisher: Within the Outer Product Span Space

来源:Arxiv_logoArxiv
英文摘要

Recent Diffusion models (DMs) advancements have explored incorporating the second-order diffusion Fisher information (DF), defined as the negative Hessian of log density, into various downstream tasks and theoretical analysis. However, current practices typically approximate the diffusion Fisher by applying auto-differentiation to the learned score network. This black-box method, though straightforward, lacks any accuracy guarantee and is time-consuming. In this paper, we show that the diffusion Fisher actually resides within a space spanned by the outer products of score and initial data. Based on the outer-product structure, we develop two efficient approximation algorithms to access the trace and matrix-vector multiplication of DF, respectively. These algorithms bypass the auto-differentiation operations with time-efficient vector-product calculations. Furthermore, we establish the approximation error bounds for the proposed algorithms. Experiments in likelihood evaluation and adjoint optimization demonstrate the superior accuracy and reduced computational cost of our proposed algorithms. Additionally, based on the novel outer-product formulation of DF, we design the first numerical verification experiment for the optimal transport property of the general PF-ODE deduced map.

Fangyikang Wang、Hubery Yin、Shaobin Zhuang、Huminhao Zhu、Yinan Li、Lei Qian、Chao Zhang、Hanbin Zhao、Hui Qian、Chen Li

计算技术、计算机技术

Fangyikang Wang,Hubery Yin,Shaobin Zhuang,Huminhao Zhu,Yinan Li,Lei Qian,Chao Zhang,Hanbin Zhao,Hui Qian,Chen Li.Efficiently Access Diffusion Fisher: Within the Outer Product Span Space[EB/OL].(2025-05-29)[2025-06-15].https://arxiv.org/abs/2505.23264.点此复制

评论