Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees

• URL: http://arxiv.org/abs/2606.16610v1
• Date: Mon, 15 Jun 2026 12:00:13 GMT
• Title: Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees
• Abstract summary: We provide convergence guarantees for Brownian motion based DFMs, focusing on the discretization error.<n>Our analysis is conducted under the Kullback-Leibler (KL) divergence and the 2-Wasserstein distance.
• Score: 15.697611355182005
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion Flow Matching (DFM) has recently emerged as a versatile framework for generative modeling, yet its theoretical convergence properties remain only partially understood. In this work, we provide refined and novel convergence guarantees for Brownian motion based DFMs, focusing on the discretization error. Our analysis is conducted under the Kullback-Leibler (KL) divergence and the 2-Wasserstein distance. Under finite-moment conditions and a mild score integrability assumption, we derive KL convergence bounds with improved dimensional dependence compared to prior work, achieving, up to our knowledge, state-of-the-art scaling under minimal conditions. We further extend the analysis to the 2-Wasserstein distance: under an additional first-order score integrability assumption and a weak log-concavity condition, we obtain convergence guarantees with dimensional dependence consistent with the KL case.

Related papers

• Decentralized Proximal Stochastic Gradient Langevin Dynamics [4.385194124090593]
  Decentralized Proximal Gradient Langevin Dynamics (DE-PSGLD) for sampling from a log-concave probability distribution constrained to a convex domain.<n>As the first decentralized approach for constrained domains, our algorithm exhibits fast posterior concentration and high predictive accuracy.
  arXiv  Detail & Related papers  (2026-05-01T15:11:06Z)
• Sharp Convergence Rates for Masked Diffusion Models [53.117058231393834]
  We develop a total-variation based analysis for the Euler method that overcomes limitations.<n>Our results relax assumptions on score estimation, improve parameter dependencies, and establish convergence guarantees.<n>Overall, our analysis introduces a direct TV-based error decomposition along the CTMC trajectory and a decoupling-based path-wise analysis for FHS.
  arXiv  Detail & Related papers  (2026-02-26T00:47:51Z)
• Particle Dynamics for Latent-Variable Energy-Based Models [12.84928511163926]
  Latent-variable energy-based models (LVEBMs) assign a single normalized energy to joint pairs of observed data and latent variables.<n>We recast maximum-likelihood training as a saddle problem over distributions on the latent and joint gradients.<n>We prove existence and convergence under standard smoothness and dissipativity assumptions, with decay rates in KL divergence and Wasserstein-2 distance.
  arXiv  Detail & Related papers  (2025-10-17T09:04:49Z)
• Shifted Composition III: Local Error Framework for KL Divergence [12.93725028754563]
  Coupling arguments are a central tool for bounding the deviation between two processes.<n>We adapt coupling arguments to the Kullback-Leibler (KL) divergence.
  arXiv  Detail & Related papers  (2024-12-23T21:40:01Z)
• Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis [56.442307356162864]
  We study the theoretical aspects of score-based discrete diffusion models under the Continuous Time Markov Chain (CTMC) framework.<n>We introduce a discrete-time sampling algorithm in the general state space $[S]d$ that utilizes score estimators at predefined time points.<n>Our convergence analysis employs a Girsanov-based method and establishes key properties of the discrete score function.
  arXiv  Detail & Related papers  (2024-10-03T09:07:13Z)
• Flow matching achieves almost minimax optimal convergence [50.38891696297888]
  Flow matching (FM) has gained significant attention as a simulation-free generative model. This paper discusses the convergence properties of FM for large sample size under the $p$-Wasserstein distance. We establish that FM can achieve an almost minimax optimal convergence rate for $1 leq p leq 2$, presenting the first theoretical evidence that FM can reach convergence rates comparable to those of diffusion models.
  arXiv  Detail & Related papers  (2024-05-31T14:54:51Z)
• Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach [49.97755400231656]
  We show that a new accelerated DDPM sampler achieves accelerated performance for three broad distribution classes not considered before.<n>Our results show an improved dependency on the data dimension $d$ among accelerated DDPM type samplers.
  arXiv  Detail & Related papers  (2024-02-21T16:11:47Z)
• KL Convergence Guarantees for Score diffusion models under minimal data assumptions [9.618473763561418]
  A notable challenge persists in the form of a lack of comprehensive quantitative results. This article focuses on score diffusion models with fixed step size stemming from the Ornstein-Uhlenbeck semigroup and its kinetic counterpart.
  arXiv  Detail & Related papers  (2023-08-23T16:31:08Z)
• Systematic compactification of the two-channel Kondo model. III. Extended field-theoretic renormalization group analysis [44.99833362998488]
  We calculate the detailed flow for the (multi) two-channel Kondo model and its compactified versions. We gain insights into the contradistinction between the consistent vs. conventional bosonization-debosonization formalisms. In particular, we make use of renormalization-flow arguments to further justify the consistent refermionization of the parallel Kondo interaction.
  arXiv  Detail & Related papers  (2023-08-07T14:07:21Z)
• Beyond the Edge of Stability via Two-step Gradient Updates [49.03389279816152]
  Gradient Descent (GD) is a powerful workhorse of modern machine learning. GD's ability to find local minimisers is only guaranteed for losses with Lipschitz gradients. This work focuses on simple, yet representative, learning problems via analysis of two-step gradient updates.
  arXiv  Detail & Related papers  (2022-06-08T21:32:50Z)
• Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity [49.66890309455787]
  We introduce the expected co-coercivity condition, explain its benefits, and provide the first last-iterate convergence guarantees of SGDA and SCO. We prove linear convergence of both methods to a neighborhood of the solution when they use constant step-size. Our convergence guarantees hold under the arbitrary sampling paradigm, and we give insights into the complexity of minibatching.
  arXiv  Detail & Related papers  (2021-06-30T18:32:46Z)
• Linear Last-iterate Convergence in Constrained Saddle-point Optimization [48.44657553192801]
  We significantly expand the understanding of last-rate uniqueness for Optimistic Gradient Descent Ascent (OGDA) and Optimistic Multiplicative Weights Update (OMWU) We show that when the equilibrium is unique, linear lastiterate convergence is achieved with a learning rate whose value is set to a universal constant. We show that bilinear games over any polytope satisfy this condition and OGDA converges exponentially fast even without the unique equilibrium assumption.
  arXiv  Detail & Related papers  (2020-06-16T20:53:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.