paper-with-me

Papers

Interpreting diffusion score matching using normalizing flow

2021-07-21 · ICML Workshop INNF 2021 7 · Wenbo Gong, Yingzhen Li

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.

📄 PDF Abstract BibTeX arXiv:2107.10072

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Venom: A PyTorch Generative Modeling Toolkit

2026-05-17 · Liang Yan arxiv

Modern generative modeling has grown into a broad collection of related but often separately implemented paradigms, including denoising diffusion models, score-based stochastic differential equations, flow matching, vari…

Flow Matching for Scalable Simulation-Based Inference

2023-05-26 · NeurIPS 2023 11 · Maximilian Dax, Jonas Wildberger, Simon Buchholz, Stephen R. Green 외

Neural posterior estimation methods based on discrete normalizing flows have become established tools for simulation-based inference (SBI), but scaling them to high-dimensional problems can be challenging. Building on re…

Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective

2026-05-07 · Meira Iske, Carola-Bibiane Schönlieb arxiv

Many normalizing flow architectures impose regularity constraints, yet their distributional approximation properties are not fully characterized. We study the expressivity of bi-Lipschitz normalizing flows through the le…

A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models

2026-05-07 · Aditya Ranganath, Mukesh Singhal arxiv

We survey continuous-time generative modeling methods based on transporting a simple reference distribution to a data distribution via stochastic or deterministic dynamics. We present a unified framework in which diffusi…

A Variational Perspective on Diffusion-Based Generative Models and Score Matching

2021-06-05 · NeurIPS 2021 12 · Chin-wei Huang, Jae Hyun Lim, Aaron Courville

Discrete-time diffusion-based generative models and score matching methods have shown promising results in modeling high-dimensional image data. Recently, Song et al. (2021) show that diffusion processes that transform d…