mlsanityData to 14 Oct 2026

SDYN-GANs: Adversarial Learning Methods for Multistep Generative Models for General Order Stochastic Dynamics

arXiv 2302.03663 ↗First posted 7 Feb 2023cs.LG cs.NA math.DScited by 4

Not on the map. Why?

Abstract (arXiv)

We introduce adversarial learning methods for data-driven generative modeling of the dynamics of nth-order stochastic systems. Our approach builds on Generative Adversarial Networks (GANs) with generative model classes based on stable m-step stochastic numerical integrators. We introduce different formulations and training methods for learning models of stochastic dynamics based on observation of trajectory samples. We develop approaches using discriminators based on Maximum Mean Discrepancy (MMD), training protocols using conditional and marginal distributions, and methods for learning dynamic responses over different time-scales. We show how our approaches can be used for modeling physical systems to learn force-laws, damping coefficients, and noise-related parameters. The adversarial learning approaches provide methods for obtaining stable generative models for dynamic tasks including long-time prediction and developing simulations for stochastic systems.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 40 of its 181 references that are in the map. First posted on arXiv 7 Feb 2023.

Builds on

40 of 181 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  5. 2018Neural Ordinary Differential Equationscited by 3,779
  6. 2017Improved Training of Wasserstein GANscited by 2,235
  7. 2018Demystifying MMD GANscited by 1,293
  8. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
  9. 2015Generative Moment Matching Networkscited by 257
  10. 2017Gate-Variants of Gated Recurrent Unit (GRU) Neural Networkscited by 242
  11. 2015A Critical Review of Recurrent Neural Networks for Sequence Learningcited by 224
  12. 2019Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limitcited by 176
28 more
  1. 2020Physics-informed learning of governing equations from scarce datacited by 167
  2. 2021Neural SDEs as Infinite-Dimensional GANscited by 161
  3. 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 151
  4. 2016Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive controlcited by 140
  5. 2021Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and controlcited by 137
  6. 2018Physics-Informed Generative Adversarial Networks for Stochastic Differential Equationscited by 135
  7. 2017The Cramer Distance as a Solution to Biased Wasserstein Gradientscited by 119
  8. 2019Max-Sliced Wasserstein Distance and its use for GANscited by 119
  9. 2022NOMAD: Nonlinear Manifold Decoders for Operator Learningcited by 83
  10. 2018Stable Recurrent Modelscited by 66
  11. 2015Sliced Wasserstein Kernels for Probability Distributionscited by 65
  12. 2018On GANs and GMMscited by 62
  13. 2020From Fourier to Koopman: Spectral Methods for Long-term Time Series Predictioncited by 50
  14. 2021Noisy Recurrent Neural Networkscited by 42
  15. 2022Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Datacited by 42
  16. 2019Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systemscited by 25
  17. 2019How Well Do WGANs Estimate the Wasserstein Metric?cited by 17
  18. 2019Contracting Implicit Recurrent Neural Networks: Stable Models with Improved Trainabilitycited by 17
  19. 2015Synthesis of recurrent neural networks for dynamical system simulationcited by 16
  20. 2018Deep learning algorithm for data-driven simulation of noisy dynamical systemcited by 12
  21. 2019Coercing Machine Learning to Output Physically Accurate Resultscited by 10
  22. 2018Enforcing constraints for interpolation and extrapolation in Generative Adversarial Networkscited by 8
  23. 2019Meshfree Methods on Manifolds for Hydrodynamic Flows on Curved Surfaces: A Generalized Moving Least-Squares (GMLS) Approachcited by 7
  24. 2022GD-VAEs: Geometric Dynamic Variational Autoencoders for Learning Nonlinear Dynamics and Dimension Reductionscited by 7
  25. 2019Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensorscited by 4
  26. 2019AReS and MaRS - Adversarial and MMD-Minimizing Regression for SDEscited by 4
  27. 2020GANs with Conditional Independence Graphs: On Subadditivity of Probability Divergencescited by 1
  28. 2022Magnus Exponential Integrators for Stiff Time-Varying Stochastic Systemscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 3.

4 papers.

  1. 2025Stochastic and Non-local Closure Modeling for Nonlinear Dynamical Systems via Latent Score-based Generative Modelscited by 4
  2. 2023Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networkscited by 1
  3. 2025Transferable Foundation Models for Geometric Tasks on Point Cloud Representations: Geometric Neural Operatorscited by 1
  4. 2025Learning Kinetic Monte Carlo stochastic dynamics with Deep Generative Adversarial Networkscited by 0