mlsanityData to 14 Oct 2026

Lipschitz-regularized gradient flows and generative particle algorithms for high-dimensional scarce data

arXiv 2210.17230 ↗First posted 31 Oct 2022stat.ML cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

We build a new class of generative algorithms capable of efficiently learning an arbitrary target distribution from possibly scarce, high-dimensional data and subsequently generate new samples. These generative algorithms are particle-based and are constructed as gradient flows of Lipschitz-regularized Kullback-Leibler or other f-divergences, where data from a source distribution can be stably transported as particles, towards the vicinity of the target distribution. As a highlighted result in data integration, we demonstrate that the proposed algorithms correctly transport gene expression data points with dimension exceeding 54K, while the sample size is typically only in the hundreds.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 29 of its 76 references that are in the map. First posted on arXiv 31 Oct 2022.

Builds on

29 of 76 references.

References · 29

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  6. 2018Neural Ordinary Differential Equationscited by 3,779
  7. 2017Improved Training of Wasserstein GANscited by 2,235
  8. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  9. 2016Least Squares Generative Adversarial Networkscited by 1,001
  10. 2021Score-based Generative Modeling in Latent Spacecited by 636
  11. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 507
  12. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
17 more
  1. 2017Learning Generative Models with Sinkhorn Divergencescited by 314
  2. 2020Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densitiescited by 250
  3. 2015Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithmcited by 197
  4. 2016Stochastic Optimization for Large-scale Optimal Transportcited by 189
  5. 2017Stein Variational Gradient Descent as Gradient Flowcited by 152
  6. 2020OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transportcited by 143
  7. 2019Maximum Mean Discrepancy Gradient Flowcited by 127
  8. 2020Interacting particle solutions of Fokker-Planck equations through gradient-log-density estimationcited by 88
  9. 2020Multiscale Simulations of Complex Systems by Learning their Effective Dynamicscited by 86
  10. 2022Probability flow solution of the Fokker-Planck equationcited by 47
  11. 2021KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Supportcited by 37
  12. 2018Scaling limit of the Stein variational gradient descent: the mean field regimecited by 35
  13. 2018Coarse-Graining Auto-Encoders for Molecular Dynamicscited by 30
  14. 2017Continuous-Time Flows for Efficient Inference and Density Estimationcited by 21
  15. 2022Structure-preserving GANscited by 17
  16. 2020Optimizing Variational Representations of Divergences and Accelerating their Statistical Estimationcited by 15
  17. 2019Formulation and properties of a divergence used to compare probability measures without absolute continuitycited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 1; 2026: 3.

8 papers.

  1. 2024Wasserstein proximal operators describe score-based generative models and resolve memorizationcited by 14
  2. 2026Sobolev Regularized MMD Gradient Flowcited by 6
  3. 2024Robust Generative Learning with Lipschitz-Regularized α-Divergences Allows Minimal Assumptions on Target Distributionscited by 4
  4. 2024Combining Wasserstein-1 and Wasserstein-2 proximals: robust manifold learning via well-posed generative flowscited by 4
  5. 2024Nonlinear denoising score matching for enhanced learning of structured distributionscited by 3
  6. 2025Proximal optimal transport divergencescited by 3
  7. 2026Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flowscited by 1
  8. 2026Graph-Informed Adversarial Modeling: Infimal Subadditivity of Interpolative Divergencescited by 0