Flow Straight and Fast in Hilbert Space: Functional Rectified Flow

• URL: http://arxiv.org/abs/2509.10384v1
• Date: Fri, 12 Sep 2025 16:18:16 GMT
• Title: Flow Straight and Fast in Hilbert Space: Functional Rectified Flow
• Authors: Jianxin Zhang, Clayton Scott,
• Abstract summary: We establish a rigorous functional formulation of rectified flow in an infinite-dimensional Hilbert space.<n>We show that this framework extends naturally to functional flow matching and functional probability flow ODEs.<n>Our method achieves superior performance compared to existing functional generative models.
• Score: 14.747544527069804
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many generative models originally developed in finite-dimensional Euclidean space have functional generalizations in infinite-dimensional settings. However, the extension of rectified flow to infinite-dimensional spaces remains unexplored. In this work, we establish a rigorous functional formulation of rectified flow in an infinite-dimensional Hilbert space. Our approach builds upon the superposition principle for continuity equations in an infinite-dimensional space. We further show that this framework extends naturally to functional flow matching and functional probability flow ODEs, interpreting them as nonlinear generalizations of rectified flow. Notably, our extension to functional flow matching removes the restrictive measure-theoretic assumptions in the existing theory of \citet{kerrigan2024functional}. Furthermore, we demonstrate experimentally that our method achieves superior performance compared to existing functional generative models.

Related papers

• Infinite dimensional generative sensing [0.9749560288448113]
  This work presents a rigorous framework for generative compressed sensing in Hilbert spaces.<n>Thanks to a generalization of the Restricted Isometry Property, we show that stable recovery holds when the number of measurements is proportional to the prior's intrinsic dimension.
  arXiv  Detail & Related papers  (2026-03-03T17:52:18Z)
• Functional Mean Flow in Hilbert Space [21.770924847119478]
  We present Functional Mean Flow (FMF) as a one-step generative model defined in infinite-dimensional Hilbert space.<n>FMF extends the one-step Mean Flow framework to functional domains by providing a theoretical formulation for Functional Flow Matching and a practical implementation for efficient training and sampling.
  arXiv  Detail & Related papers  (2025-11-17T02:38:28Z)
• Probability-Flow ODE in Infinite-Dimensional Function Spaces [26.795793417392037]
  We derive, for the first time, an analog of the probability-flow ODE (PF-ODE) in infinite-dimensional function spaces.<n>We reduce the number of function evaluations while maintaining sample quality in function generation tasks, including applications to PDEs.
  arXiv  Detail & Related papers  (2025-03-13T10:01:00Z)
• Kernel Operator-Theoretic Bayesian Filter for Nonlinear Dynamical Systems [25.922732994397485]
  We propose a machine-learning alternative based on a functional Bayesian perspective for operator-theoretic modeling. This formulation is directly done in an infinite-dimensional space of linear operators or Hilbert space with universal approximation property. We demonstrate that this practical approach can obtain accurate results and outperform finite-dimensional Koopman decomposition.
  arXiv  Detail & Related papers  (2024-10-31T20:31:31Z)
• Stochastic Optimal Control for Diffusion Bridges in Function Spaces [13.544676987441441]
  We present a theory of optimal control tailored to infinite-dimensional spaces.<n>We show how Doob's $h$-transform can be derived from the SOC perspective and expanded to infinite dimensions.<n>We propose two applications: learning bridges between two infinite-dimensional distributions and generative models for sampling from an infinite-dimensional distribution.
  arXiv  Detail & Related papers  (2024-05-31T05:42:47Z)
• Functional Diffusion [55.251174506648454]
  We propose a new class of generative diffusion models, called functional diffusion. functional diffusion can be seen as an extension of classical diffusion models to an infinite-dimensional domain. We show generative results on complicated signed distance functions and deformation functions defined on 3D surfaces.
  arXiv  Detail & Related papers  (2023-11-26T21:35:34Z)
• Third quantization of open quantum systems: new dissipative symmetries and connections to phase-space and Keldysh field theory formulations [77.34726150561087]
  We reformulate the technique of third quantization in a way that explicitly connects all three methods. We first show that our formulation reveals a fundamental dissipative symmetry present in all quadratic bosonic or fermionic Lindbladians. For bosons, we then show that the Wigner function and the characteristic function can be thought of as ''wavefunctions'' of the density matrix.
  arXiv  Detail & Related papers  (2023-02-27T18:56:40Z)
• Continuous percolation in a Hilbert space for a large system of qubits [58.720142291102135]
  The percolation transition is defined through the appearance of the infinite cluster. We show that the exponentially increasing dimensionality of the Hilbert space makes its covering by finite-size hyperspheres inefficient. Our approach to the percolation transition in compact metric spaces may prove useful for its rigorous treatment in other contexts.
  arXiv  Detail & Related papers  (2022-10-15T13:53:21Z)
• Experimental Design for Linear Functionals in Reproducing Kernel Hilbert Spaces [102.08678737900541]
  We provide algorithms for constructing bias-aware designs for linear functionals. We derive non-asymptotic confidence sets for fixed and adaptive designs under sub-Gaussian noise.
  arXiv  Detail & Related papers  (2022-05-26T20:56:25Z)
• Neural Manifold Ordinary Differential Equations [46.25832801867149]
  We introduce Neural Manifold Ordinary Differential Equations, which enables the construction of Manifold Continuous Normalizing Flows (MCNFs) MCNFs require only local geometry and compute probabilities with continuous change of variables. We find that leveraging continuous manifold dynamics produces a marked improvement for both density estimation and downstream tasks.
  arXiv  Detail & Related papers  (2020-06-18T03:24:58Z)
• Quantum Geometric Confinement and Dynamical Transmission in Grushin Cylinder [68.8204255655161]
  We classify the self-adjoint realisations of the Laplace-Beltrami operator minimally defined on an infinite cylinder. We retrieve those distinguished extensions previously identified in the recent literature, namely the most confining and the most transmitting.
  arXiv  Detail & Related papers  (2020-03-16T11:37:23Z)

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.