ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2305.16860
15
31

Error Bounds for Flow Matching Methods

26 May 2023
Joe Benton
George Deligiannidis
Arnaud Doucet
    DiffM
ArXivPDFHTML
Abstract

Score-based generative models are a popular class of generative modelling techniques relying on stochastic differential equations (SDE). From their inception, it was realized that it was also possible to perform generation using ordinary differential equations (ODE) rather than SDE. This led to the introduction of the probability flow ODE approach and denoising diffusion implicit models. Flow matching methods have recently further extended these ODE-based approaches and approximate a flow between two arbitrary probability distributions. Previous work derived bounds on the approximation error of diffusion models under the stochastic sampling regime, given assumptions on the L2L^2L2 loss. We present error bounds for the flow matching procedure using fully deterministic sampling, assuming an L2L^2L2 bound on the approximation error and a certain regularity condition on the data distributions.

View on arXiv
Comments on this paper