Efficiently Access Diffusion Fisher: Within the Outer Product Span Space

TL;DR

This paper introduces efficient algorithms to approximate diffusion Fisher information within diffusion models, leveraging an outer-product structure to improve accuracy and computational speed over traditional auto-differentiation methods.

Contribution

The paper reveals that diffusion Fisher resides in an outer-product span space and develops two algorithms to efficiently approximate it, with proven error bounds and practical advantages.

Findings

Algorithms outperform auto-differentiation in accuracy and speed

Established error bounds for the approximation algorithms

Demonstrated effectiveness in likelihood evaluation and optimization tasks

Abstract

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.