Deterministic Decomposition of Stochastic Generative Dynamics

• URL: http://arxiv.org/abs/2605.08794v2
• Date: Sat, 16 May 2026 05:38:25 GMT
• Title: Deterministic Decomposition of Stochastic Generative Dynamics
• Abstract summary: We propose a flow-based framework for learning generative dynamics through both marginal and conditional formulations.<n>We show that the proposed decomposition enables interpretable and controllable sampling by adjusting the osmotic contribution in probability transport.
• Score: 4.949940153151258
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern generative models can be understood as probability transport from a simple base distribution to a target data distribution. Deterministic transport models offer tractable velocity-field parameterizations, whereas stochastic generative models capture richer density evolution through drift and diffusion. Yet when stochastic dynamics are described through deterministic velocity fields, the effects of drift and diffusion are often compressed into a single effective field, obscuring the distinct roles of deterministic evolution and stochastic fluctuation. In this work, we show that the deterministic field \(b_t\) of a stochastic generative process admits a natural transport--osmotic decomposition that separates deterministic transport from stochastic, diffusion-induced effects: \(b_t = u_t + d_t\), where \(u_t\) governs marginal probability transport and \(d_t\) captures an osmotic effect induced by diffusion and determined by the marginal score. Based on this decomposition, we propose Bridge Matching, a flow-based framework for learning decomposed generative dynamics through both marginal and conditional formulations. In generative modeling experiments, we recombine the learned components as \(b_t = u_t + λ_d d_t\), showing that the proposed decomposition enables interpretable and controllable sampling by adjusting the osmotic contribution in probability transport.

Related papers

• A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models [0.3222802562733787]
  We survey continuous-time generative modeling methods based on transporting a simple reference distribution to a data distribution via deterministic dynamics.<n>We present a unified framework in which diffusion models, score-based generative models, and flow matching are instances of learning a time-dependent vector field.
  arXiv  Detail & Related papers  (2026-05-07T18:32:15Z)
• Interpolating Discrete Diffusion Models with Controllable Resampling [49.771004594828405]
  Masked diffusion models suffer from irreversible errors due to early unmasking.<n>Uniform diffusion models, despite enabling self-correction, often yield low-quality samples.<n>We introduce Interpolating Discrete Diffusion Model, that improves diffusion by reducing dependence on intermediate latent states.
  arXiv  Detail & Related papers  (2026-04-19T07:55:57Z)
• Differentiable Stochastic Traffic Dynamics: Physics-Informed Generative Modelling in Transportation [0.0]
  This work develops a framework in which the physics constraint itself is distributional and spatial, derived from traffic-flow dynamics.<n>The framework provides a basis for distributional traffic-state estimation and for fundamental analysis in a physics-informed generative setting.
  arXiv  Detail & Related papers  (2026-03-10T04:25:20Z)
• Weighted Stochastic Differential Equation to Implement Wasserstein-Fisher-Rao Gradient Flow [0.0]
  A promising line of work leverages tools from information geometry to augment diffusion-based samplers with mass reweighting mechanisms.<n>Our work provides a preliminary but rigorous investigation of WFR-based sampling dynamics, and aims to clarify their theoretical structure as a foundation for future developments.
  arXiv  Detail & Related papers  (2025-12-19T18:31:27Z)
• Overcoming Dimensional Factorization Limits in Discrete Diffusion Models through Quantum Joint Distribution Learning [79.65014491424151]
  We propose a quantum Discrete Denoising Diffusion Probabilistic Model (QD3PM)<n>It enables joint probability learning through diffusion and denoising in exponentially large Hilbert spaces.<n>This paper establishes a new theoretical paradigm in generative models by leveraging the quantum advantage in joint distribution learning.
  arXiv  Detail & Related papers  (2025-05-08T11:48:21Z)
• Inferring Parameter Distributions in Heterogeneous Motile Particle Ensembles: A Likelihood Approach for Second Order Langevin Models [0.8274836883472768]
  Inference methods are required to understand and predict the motion patterns from time discrete trajectory data provided by experiments. We propose a new method to approximate the likelihood for non-linear second order Langevin models. We thereby pave the way for the systematic, data-driven inference of dynamical models for actively driven entities.
  arXiv  Detail & Related papers  (2024-11-13T15:27:02Z)
• Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian Mixture Models [59.331993845831946]
  Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. This paper provides the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models.
  arXiv  Detail & Related papers  (2024-03-03T23:15:48Z)
• Equivariant Flow Matching with Hybrid Probability Transport [69.11915545210393]
  Diffusion Models (DMs) have demonstrated effectiveness in generating feature-rich geometries. DMs typically suffer from unstable probability dynamics with inefficient sampling speed. We introduce geometric flow matching, which enjoys the advantages of both equivariant modeling and stabilized probability dynamics.
  arXiv  Detail & Related papers  (2023-12-12T11:13:13Z)
• Formulating Discrete Probability Flow Through Optimal Transport [29.213216002178306]
  We first prove that the continuous probability flow is the Monge optimal transport map under certain conditions, and also present an equivalent evidence for discrete cases. We then define the discrete probability flow in line with the principles of optimal transport. Experiments on the synthetic toy dataset and the CIFAR-10 dataset have validated our proposed discrete probability flow.
  arXiv  Detail & Related papers  (2023-11-07T11:03:27Z)
• Score-based Continuous-time Discrete Diffusion Models [102.65769839899315]
  We extend diffusion models to discrete variables by introducing a Markov jump process where the reverse process denoises via a continuous-time Markov chain. We show that an unbiased estimator can be obtained via simple matching the conditional marginal distributions. We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.
  arXiv  Detail & Related papers  (2022-11-30T05:33:29Z)
• Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization [106.70006655990176]
  A distributional optimization problem arises widely in machine learning and statistics. We propose a novel particle-based algorithm, dubbed as variational transport, which approximately performs Wasserstein gradient descent. We prove that when the objective function satisfies a functional version of the Polyak-Lojasiewicz (PL) (Polyak, 1963) and smoothness conditions, variational transport converges linearly.
  arXiv  Detail & Related papers  (2020-12-21T18:33:13Z)

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.