Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching

• URL: http://arxiv.org/abs/2512.01286v1
• Date: Mon, 01 Dec 2025 05:14:25 GMT
• Title: Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching
• Authors: Mudit Gaur, Prashant Trivedi, Shuchin Aeron, Amrit Singh Bedi, George K. Atia, Vaneet Aggarwal,
• Abstract summary: We provide the first analysis of the sample complexity for flow-matching based generative models.<n>We decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field.
• Score: 60.37045080890305
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows governed by ordinary differential equations. Despite growing empirical success, the theoretical understanding of flow matching remains limited, particularly in terms of sample complexity results. In this work, we provide the first analysis of the sample complexity for flow-matching based generative models without assuming access to the empirical risk minimizer (ERM) of the loss function for estimating the velocity field. Under standard assumptions on the loss function for velocity field estimation and boundedness of the data distribution, we show that a sufficiently expressive neural network can learn a velocity field such that with $\mathcal{O}(ε^{-4})$ samples, such that the Wasserstein-2 distance between the learned and the true distribution is less than $\mathcal{O}(ε)$. The key technical idea is to decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field. Each of these terms are then handled via techniques that may be of independent interest.

Related papers

• FlowConsist: Make Your Flow Consistent with Real Trajectory [99.22869983378062]
  We argue that current fast-flow training paradigms suffer from two fundamental issues.<n> conditional velocities constructed from randomly paired noise-data samples introduce systematic trajectory drift.<n>We propose FlowConsist, a training framework designed to enforce trajectory consistency in fast flows.
  arXiv  Detail & Related papers  (2026-02-06T03:24:23Z)
• Temporal Pair Consistency for Variance-Reduced Flow Matching [13.328987133593154]
  Temporal Pair Consistency (TPC) is a lightweight variance-reduction principle that couples velocity predictions at paired timesteps along the same probability path.<n>Instantiated within flow matching, TPC improves sample quality and efficiency across CIFAR-10 and ImageNet at multiple resolutions.
  arXiv  Detail & Related papers  (2026-02-04T00:05:21Z)
• Order-Optimal Sample Complexity of Rectified Flows [43.61958734990224]
  We study rectified flow models, which constrain transport trajectories to be linear from the base distribution to the data distribution.<n>This structural restriction greatly accelerates sampling, often enabling high-quality generation with a single step.
  arXiv  Detail & Related papers  (2026-01-28T04:55:14Z)
• Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models [100.28111930893188]
  Some of today's best generative models still require hundreds to thousands of neural function evaluations to compute a single likelihood.<n>We present fast flow joint distillation (F2D2), a framework that simultaneously reduces the number of NFEs required for both sampling and likelihood evaluation by two orders of magnitude.<n>F2D2 is modular, compatible with existing flow-based few-step sampling models, and requires only an additional divergence prediction head.
  arXiv  Detail & Related papers  (2025-12-02T10:48:20Z)
• Dimension-free error estimate for diffusion model and optimal scheduling [22.20348860913421]
  Diffusion generative models have emerged as powerful tools for producing synthetic data from an empirically observed distribution.<n>Previous analyses have quantified the error between the generated and the true data distributions in terms of Wasserstein distance or Kullback-Leibler divergence.<n>In this work, we derive an explicit, dimension-free bound on the discrepancy between the generated and the true data distributions.
  arXiv  Detail & Related papers  (2025-12-01T15:58:20Z)
• Neural Flow Samplers with Shortcut Models [19.81513273510523]
  Continuous flow-based neural samplers offer a promising approach to generate samples from unnormalized densities.<n>We introduce an improved estimator for these challenging quantities, employing a velocity-driven Sequential Monte Carlo method.<n>Our proposed Neural Flow Shortcut Sampler empirically outperforms existing flow-based neural samplers on both synthetic datasets and complex n-body system targets.
  arXiv  Detail & Related papers  (2025-02-11T07:55:41Z)
• MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation [48.41289705783405]
  We propose a PDE-embedded network with multiscale time stepping (MultiPDENet)<n>In particular, we design a convolutional filter based on the structure of finite difference with a small number of parameters to optimize.<n>A Physics Block with a 4th-order Runge-Kutta integrator at the fine time scale is established that embeds the structure of PDEs to guide the prediction.
  arXiv  Detail & Related papers  (2025-01-27T12:15:51Z)
• On the Wasserstein Convergence and Straightness of Rectified Flow [54.580605276017096]
  Rectified Flow (RF) is a generative model that aims to learn straight flow trajectories from noise to data.<n>We provide a theoretical analysis of the Wasserstein distance between the sampling distribution of RF and the target distribution.<n>We present general conditions guaranteeing uniqueness and straightness of 1-RF, which is in line with previous empirical findings.
  arXiv  Detail & Related papers  (2024-10-19T02:36:11Z)
• Characteristic Learning for Provable One Step Generation [12.620728925515012]
  We propose a one-step generative model that combines the efficiency of sampling in Generative Adversarial Networks (GANs) with the stable performance of flow-based models.<n>Our model is driven by characteristics, along which the probability density transport can be described by ordinary differential equations (ODEs)<n>A deep neural network is then trained to fit these characteristics, creating a one-step map that pushes a simple Gaussian distribution to the target distribution.
  arXiv  Detail & Related papers  (2024-05-09T02:41:42Z)
• Deep conditional distribution learning via conditional Föllmer flow [12.035609693882856]
  We introduce an ordinary differential equation (ODE) based deep generative method for learning conditional distributions, named Conditional F"ollmer Flow.<n>For effective implementation, we discretize the flow with Euler's method where we estimate the velocity field nonparametrically using a deep neural network.
  arXiv  Detail & Related papers  (2024-02-02T14:52:10Z)
• Efficient CDF Approximations for Normalizing Flows [64.60846767084877]
  We build upon the diffeomorphic properties of normalizing flows to estimate the cumulative distribution function (CDF) over a closed region. Our experiments on popular flow architectures and UCI datasets show a marked improvement in sample efficiency as compared to traditional estimators.
  arXiv  Detail & Related papers  (2022-02-23T06:11:49Z)

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.