mlsanityData to 13 Oct 2026

Diffeomorphic Measure Matching with Kernels for Generative Modeling

arXiv 2402.08077 ↗First posted 12 Feb 2024stat.ML cs.LG math.DScited by 4

Not on the map. Why?

Abstract (arXiv)

This article presents a general framework for the transport of probability measures towards minimum divergence generative modeling and sampling using ordinary differential equations (ODEs) and Reproducing Kernel Hilbert Spaces (RKHSs), inspired by ideas from diffeomorphic matching and image registration. A theoretical analysis of the proposed method is presented, giving a priori error bounds in terms of the complexity of the model, the number of samples in the training set, and model misspecification. An extensive suite of numerical experiments further highlights the properties, strengths, and weaknesses of the method and extends its applicability to other tasks, such as conditional simulation and inference.

Key facts. Cited by 4 papers in the map (data through 13 Oct 2026). Builds on 41 of its 92 references that are in the map. First posted on arXiv 12 Feb 2024.

Builds on

41 of 92 references.

References · 41

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,028
  2. 2018Neural Ordinary Differential Equationscited by 3,750
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,295
  4. 2017Improved Training of Wasserstein GANscited by 2,226
  5. 2015Variational Inference with Normalizing Flowscited by 2,163
  6. 2016Variational Inference: A Review for Statisticianscited by 1,469
  7. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,317
  8. 2018Demystifying MMD GANscited by 1,277
  9. 2022Building Normalizing Flows with Stochastic Interpolantscited by 979
  10. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 917
  11. 2018Computational Optimal Transportcited by 772
  12. 2017Masked Autoregressive Flow for Density Estimationcited by 680
29 more
  1. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 588
  2. 2016Kernel Mean Embedding of Distributions: A Review and Beyondcited by 360
  3. 2017MMD GAN: Towards Deeper Understanding of Moment Matching Networkcited by 252
  4. 2022A Survey on Generative Diffusion Modelcited by 240
  5. 2017Advances in Variational Inferencecited by 236
  6. 2018Deep Neural Networks Motivated by Partial Differential Equationscited by 187
  7. 2020OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transportcited by 143
  8. 2019Deep Learning via Dynamical Systems: An Approximation Perspectivecited by 78
  9. 2015Operator-valued Kernels for Learning from Functional Response Datacited by 59
  10. 2021Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projectionscited by 53
  11. 2019Statistical Inference for Generative Models with Maximum Mean Discrepancycited by 43
  12. 2020Conditional Sampling with Monotone GANs: from Generative Models to Likelihood-Free Inferencecited by 41
  13. 2017Optimal Transport for Diffeomorphic Registrationcited by 39
  14. 2014Dimension-independent likelihood-informed MCMCcited by 37
  15. 2022Universal approximation property of invertible neural networkscited by 30
  16. 2015Fast Optimal Transport Averaging of Neuroimaging Datacited by 26
  17. 2016Wasserstein Discriminant Analysiscited by 25
  18. 2023Distribution learning via neural differential equations: a nonparametric statistical perspectivecited by 22
  19. 2022Optimal transport map estimation in general function spacescited by 20
  20. 2023Minimax estimation of discontinuous optimal transport maps: The semi-discrete casecited by 20
  21. 2023Efficient Neural Network Approaches for Conditional Optimal Transport with Applications in Bayesian Inferencecited by 20
  22. 2014The Geometric Foundations of Hamiltonian Monte Carlocited by 19
  23. 2022An improved central limit theorem and fast convergence rates for entropic transportation costscited by 18
  24. 2022On minimax density estimation via measure transportcited by 18
  25. 2020Do ideas have shape? Idea registration as the continuous limit of artificial neural networkscited by 16
  26. 2021Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Ratescited by 16
  27. 2022Wasserstein K-means for clustering probability distributionscited by 16
  28. 2015Diffeomorphic density matching by optimal information transportcited by 7
  29. 2018Diffeomorphic Learningcited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Gaussian Measures Conditioned on Nonlinear Observations: Consistency, MAP Estimators, and Simulationcited by 4
  2. 2025Iterative Flow Matching: Path Correction and Gradual Refinement for Enhanced Generative Modelingcited by 4
  3. 2026Error Analysis of Bayesian Inverse Problems with Generative Priorscited by 2
  4. 2026Wasserstein gradient flows for Coulomb discrepanciescited by 2