pith. sign in

arxiv: 2107.10072 · v1 · pith:M7KZ6Q4Dnew · submitted 2021-07-21 · 💻 cs.LG · stat.ML

Interpreting diffusion score matching using normalizing flow

classification 💻 cs.LG stat.ML
keywords diffusionmatchingmatrixdiscrepancyscoresteinflownormalizing
0
0 comments X
read the original abstract

Scoring matching (SM), and its related counterpart, Stein discrepancy (SD) have achieved great success in model training and evaluations. However, recent research shows their limitations when dealing with certain types of distributions. One possible fix is incorporating the original score matching (or Stein discrepancy) with a diffusion matrix, which is called diffusion score matching (DSM) (or diffusion Stein discrepancy (DSD)). However, the lack of interpretation of the diffusion limits its usage within simple distributions and manually chosen matrix. In this work, we plan to fill this gap by interpreting the diffusion matrix using normalizing flows. Specifically, we theoretically prove that DSM (or DSD) is equivalent to the original score matching (or Stein discrepancy) evaluated in the transformed space defined by the normalizing flow, where the diffusion matrix is the inverse of the flow's Jacobian matrix. In addition, we also build its connection to Riemannian manifolds and further extend it to continuous flows, where the change of DSM is characterized by an ODE.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Robust ensemble Kalman filtering under observation noise misspecification via diffusion score matching

    math.ST 2026-05 unverdicted novelty 7.0

    A diffusion score matching based Kalman filter is developed for robust ensemble filtering under observation noise misspecification, with theoretical guarantees and ensemble implementations tested on Lorenz systems.