Carré du champ flow matching: better quality-generalisation tradeoff in generative models

• URL: http://arxiv.org/abs/2510.05930v1
• Date: Tue, 07 Oct 2025 13:41:33 GMT
• Title: Carré du champ flow matching: better quality-generalisation tradeoff in generative models
• Authors: Jacob Bamberger, Iolo Jones, Dennis Duncan, Michael M. Bronstein, Pierre Vandergheynst, Adam Gosztolai,
• Abstract summary: Carr'e du champ flow matching (CDC-FM) is a generalisation of flow matching (FM)<n>We show that CDC-FM consistently offers a better quality-generalisation tradeoff.<n>Our work provides a mathematical framework for studying the interplay between data geometry, generalisation and memorisation in generative models.
• Score: 24.078205139029546
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep generative models often face a fundamental tradeoff: high sample quality can come at the cost of memorisation, where the model reproduces training data rather than generalising across the underlying data geometry. We introduce Carr\'e du champ flow matching (CDC-FM), a generalisation of flow matching (FM), that improves the quality-generalisation tradeoff by regularising the probability path with a geometry-aware noise. Our method replaces the homogeneous, isotropic noise in FM with a spatially varying, anisotropic Gaussian noise whose covariance captures the local geometry of the latent data manifold. We prove that this geometric noise can be optimally estimated from the data and is scalable to large data. Further, we provide an extensive experimental evaluation on diverse datasets (synthetic manifolds, point clouds, single-cell genomics, animal motion capture, and images) as well as various neural network architectures (MLPs, CNNs, and transformers). We demonstrate that CDC-FM consistently offers a better quality-generalisation tradeoff. We observe significant improvements over standard FM in data-scarce regimes and in highly non-uniformly sampled datasets, which are often encountered in AI for science applications. Our work provides a mathematical framework for studying the interplay between data geometry, generalisation and memorisation in generative models, as well as a robust and scalable algorithm that can be readily integrated into existing flow matching pipelines.

Related papers

• Riemannian AmbientFlow: Towards Simultaneous Manifold Learning and Generative Modeling from Corrupted Data [4.681760167323748]
  We introduce a framework for learning a probabilistic generative model and the underlying, nonlinear data manifold directly from corrupted observations.<n>We establish theoretical guarantees showing that, under appropriate geometric regularization and measurement conditions, the learned model recovers the underlying data distribution up to a controllable error and yields a smooth, bi-Lipschitz manifold parametrization.
  arXiv  Detail & Related papers  (2026-01-26T17:51:52Z)
• Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds [32.40675406199536]
  Generalised Flow Maps (GFM) is a new class of few-step generative models.<n>We benchmark GFMs against other geometric generative models on a suite of geometric datasets.
  arXiv  Detail & Related papers  (2025-10-24T16:14:31Z)
• Wavelet Flow For Extragalactic Foreground Simulations [0.0]
  Extragalactic foregrounds in cosmic microwave background (CMB) observations are a source of cosmological and astrophysical information.<n>We explore the use of Wavelet Flow (WF) models to tackle the novel task of modeling the field-level probability distributions of CMB secondaries and foreground.
  arXiv  Detail & Related papers  (2025-05-27T14:08:28Z)
• Elucidating Flow Matching ODE Dynamics with Respect to Data Geometries and Denoisers [10.947094609205765]
  Flow matching (FM) models extend ODE sampler based diffusion models into a general framework.<n>A rigorous theoretical analysis of FM models is essential for sample quality, stability, and broader applicability.<n>In this paper, we advance the theory of FM models through a comprehensive analysis of sample trajectories.
  arXiv  Detail & Related papers  (2024-12-25T01:17:15Z)
• Categorical Flow Matching on Statistical Manifolds [12.646272756981672]
  We introduce a flow-matching framework on the manifold of parameterized probability measures inspired by information geometry.<n>We develop an efficient training and sampling algorithm that overcomes numerical stability with a diffeomorphism between manifold.<n>We manifest that SFM can learn more complex patterns on the statistical manifold where existing models often fail due to strong prior assumptions.
  arXiv  Detail & Related papers  (2024-05-26T05:50:39Z)
• RGM: A Robust Generalizable Matching Model [49.60975442871967]
  We propose a deep model for sparse and dense matching, termed RGM (Robust Generalist Matching) To narrow the gap between synthetic training samples and real-world scenarios, we build a new, large-scale dataset with sparse correspondence ground truth. We are able to mix up various dense and sparse matching datasets, significantly improving the training diversity.
  arXiv  Detail & Related papers  (2023-10-18T07:30:08Z)
• VTAE: Variational Transformer Autoencoder with Manifolds Learning [144.0546653941249]
  Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables. The nonlinearity of the generator implies that the latent space shows an unsatisfactory projection of the data space, which results in poor representation learning. We show that geodesics and accurate computation can substantially improve the performance of deep generative models.
  arXiv  Detail & Related papers  (2023-04-03T13:13:19Z)
• Decision Forest Based EMG Signal Classification with Low Volume Dataset Augmented with Random Variance Gaussian Noise [51.76329821186873]
  We produce a model that can classify six different hand gestures with a limited number of samples that generalizes well to a wider audience. We appeal to a set of more elementary methods such as the use of random bounds on a signal, but desire to show the power these methods can carry in an online setting.
  arXiv  Detail & Related papers  (2022-06-29T23:22:18Z)
• Moser Flow: Divergence-based Generative Modeling on Manifolds [49.04974733536027]
  Moser Flow (MF) is a new class of generative models within the family of continuous normalizing flows (CNF) MF does not require invoking or backpropagating through an ODE solver during training. We demonstrate for the first time the use of flow models for sampling from general curved surfaces.
  arXiv  Detail & Related papers  (2021-08-18T09:00:24Z)
• Manifold Topology Divergence: a Framework for Comparing Data Manifolds [109.0784952256104]
  We develop a framework for comparing data manifold, aimed at the evaluation of deep generative models. Based on the Cross-Barcode, we introduce the Manifold Topology Divergence score (MTop-Divergence) We demonstrate that the MTop-Divergence accurately detects various degrees of mode-dropping, intra-mode collapse, mode invention, and image disturbance.
  arXiv  Detail & Related papers  (2021-06-08T00:30:43Z)
• Understanding Overparameterization in Generative Adversarial Networks [56.57403335510056]
  Generative Adversarial Networks (GANs) are used to train non- concave mini-max optimization problems. A theory has shown the importance of the gradient descent (GD) to globally optimal solutions. We show that in an overized GAN with a $1$-layer neural network generator and a linear discriminator, the GDA converges to a global saddle point of the underlying non- concave min-max problem.
  arXiv  Detail & Related papers  (2021-04-12T16:23:37Z)

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.