On the Regularity and Generalization of One-Step Wasserstein-guided Generative Models for PDE-Induced Measures

• URL: http://arxiv.org/abs/2605.21388v1
• Date: Wed, 20 May 2026 16:43:55 GMT
• Title: On the Regularity and Generalization of One-Step Wasserstein-guided Generative Models for PDE-Induced Measures
• Abstract summary: We develop a theoretical framework for understanding the regularity of transport maps.<n>We show that the optimal transport map from a uniform source measure to the target measure is Hlder continuous.<n>This regularity yields an approximation-theoretic justification for one-step generative models that learn PDE-induced distributions via a single pushforward map.
• Score: 3.746583479431864
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the remarkable empirical success of generative models, the available theory on their statistical accuracy in scientific computing remains largely pessimistic. This paper develops a theoretical framework for understanding the regularity of transport maps and the generalization properties of one-step Wasserstein-guided generative models for PDE-induced probability measures. We consider normalized target densities associated with linear elliptic and parabolic equations on bounded domains, as well as diffusion and Fokker--Planck equations on the torus. Under standard structural assumptions, we prove that these target measures satisfy doubling conditions. By combining this fact with regularity theory for optimal transport between doubling measures, we show that the optimal transport map from a uniform source measure to the target measure is Hölder continuous. This regularity yields an approximation-theoretic justification for one-step generative models that learn PDE-induced distributions via a single pushforward map. As a representative instance, we study DeepParticle and derive excess-risk bounds characterizing the discrepancy between the learned map and the population-optimal map. We also establish a robustness estimate under target shift and illustrate the theory with experiments which support the derived rates.

Related papers

• The Procrustean Bed of Time Series: The Optimization Bias of Point-wise Loss [53.542743390809356]
  This paper aims to provide a first-principles analysis of the Expectation of Optimization Bias (EOB)<n>Our analysis reveals a fundamental paradigm paradox: the more deterministic and structured the time series, the more severe the bias by point-wise loss function.<n>We present a concrete solution that simultaneously achieves both principles via DFT or DWT.
  arXiv  Detail & Related papers  (2025-12-21T06:08:22Z)
• Estimation of Stochastic Optimal Transport Maps [20.559434126392205]
  We introduce a novel metric for evaluating the transportation quality of maps.<n>Under this metric, we develop computationally efficient map estimators with near-optimal finite-sample risk bounds.<n>These contributions constitute the first general-purpose theory for map estimation, compatible with a wide spectrum of real-world applications.
  arXiv  Detail & Related papers  (2025-12-10T10:23:40Z)
• A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models [8.862614615192578]
  We study the large-sample properties of a likelihood-based approach for estimating conditional deep generative models.<n>Our results lead to the convergence rate of a sieve maximum likelihood estimator for estimating the conditional distribution.
  arXiv  Detail & Related papers  (2024-10-02T20:46:21Z)
• Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory [87.00653989457834]
  Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning. Despite the empirical success, theory of conditional diffusion models is largely missing. This paper bridges the gap by presenting a sharp statistical theory of distribution estimation using conditional diffusion models.
  arXiv  Detail & Related papers  (2024-03-18T17:08:24Z)
• On the Generalization Properties of Diffusion Models [31.067038651873126]
  This work embarks on a comprehensive theoretical exploration of the generalization attributes of diffusion models.<n>We establish theoretical estimates of the generalization gap that evolves in tandem with the training dynamics of score-based diffusion models.<n>We extend our quantitative analysis to a data-dependent scenario, wherein target distributions are portrayed as a succession of densities.
  arXiv  Detail & Related papers  (2023-11-03T09:20:20Z)
• End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics [61.44793171735013]
  We introduce a novel unified architecture, termed latent variation models, which combines the latent learning of cutting-edge generative art approaches with an end-to-end variational framework. Our unified approach achieves a distribution-free distance to the truth of over 20 times less than non-latent state-of-the-art baseline.
  arXiv  Detail & Related papers  (2023-05-17T17:43:10Z)
• Diffusion Models are Minimax Optimal Distribution Estimators [49.47503258639454]
  We provide the first rigorous analysis on approximation and generalization abilities of diffusion modeling. We show that when the true density function belongs to the Besov space and the empirical score matching loss is properly minimized, the generated data distribution achieves the nearly minimax optimal estimation rates.
  arXiv  Detail & Related papers  (2023-03-03T11:31:55Z)
• Matching Normalizing Flows and Probability Paths on Manifolds [57.95251557443005]
  Continuous Normalizing Flows (CNFs) are generative models that transform a prior distribution to a model distribution by solving an ordinary differential equation (ODE) We propose to train CNFs by minimizing probability path divergence (PPD), a novel family of divergences between the probability density path generated by the CNF and a target probability density path. We show that CNFs learned by minimizing PPD achieve state-of-the-art results in likelihoods and sample quality on existing low-dimensional manifold benchmarks.
  arXiv  Detail & Related papers  (2022-07-11T08:50:19Z)
• Strong posterior contraction rates via Wasserstein dynamics [8.479040075763892]
  In Bayesian statistics, posterior contraction rates (PCRs) quantify the speed at which the posterior distribution concentrates on arbitrarily small neighborhoods of a true model. We develop a new approach to PCRs, with respect to strong norm distances on parameter spaces of functions.
  arXiv  Detail & Related papers  (2022-03-21T06:53:35Z)
• On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification [101.0377583883137]
  Projection robust (PR) OT seeks to maximize the OT cost between two measures by choosing a $k$-dimensional subspace onto which they can be projected. Our first contribution is to establish several fundamental statistical properties of PR Wasserstein distances. Next, we propose the integral PR Wasserstein (IPRW) distance as an alternative to the PRW distance, by averaging rather than optimizing on subspaces.
  arXiv  Detail & Related papers  (2020-06-22T14:35:33Z)
• Learning Implicit Generative Models with Theoretical Guarantees [12.761710596142109]
  We propose a textbfunified textbfframework for textbfimplicit textbfmodeling (UnifiGem) UnifiGem integrates approaches from optimal transport, numerical ODE, density-ratio (density-difference) estimation and deep neural networks. Experimental results on both synthetic datasets and real benchmark datasets support our theoretical findings and demonstrate the effectiveness of UnifiGem.
  arXiv  Detail & Related papers  (2020-02-07T15:55:48Z)

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.