mlsanityData to 14 Oct 2026

A new local time-decoupled squared Wasserstein-2 method for training stochastic neural networks to reconstruct uncertain parameters in dynamical systems

arXiv 2503.05068 ↗First posted 7 Mar 2025cs.LG math.PRcited by 2

Not on the map. Why?

Abstract (arXiv)

In this work, we propose and analyze a new local time-decoupled squared Wasserstein-2 method for reconstructing the distribution of unknown parameters in dynamical systems. Specifically, we show that a stochastic neural network model, which can be effectively trained by minimizing our proposed local time-decoupled squared Wasserstein-2 loss function, is an effective model for approximating the distribution of uncertain model parameters in dynamical systems. Through several numerical examples, we showcase the effectiveness of our proposed method in reconstructing the distribution of parameters in different dynamical systems.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 14 of its 52 references that are in the map. First posted on arXiv 7 Mar 2025.

Builds on

14 of 52 references.

References · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2018Neural Ordinary Differential Equationscited by 3,779
  4. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  5. 2017Improved Training of Wasserstein GANscited by 2,235
  6. 2017Train longer, generalize better: closing the generalization gap in large batch training of neural networkscited by 279
  7. 2015Generative Moment Matching Networkscited by 257
  8. 2018Statistical Aspects of Wasserstein Distancescited by 203
  9. 2017Machine Learning of Linear Differential Equations using Gaussian Processescited by 140
  10. 2020Approximation Bounds for Random Neural Networks and Reservoir Systemscited by 52
  11. 2023Gaussian random field approximation via Stein's method with applications to wide random neural networkscited by 11
  12. 2024An efficient Wasserstein-distance approach for reconstructing jump-diffusion processes using parameterized neural networkscited by 5
2 more
  1. 2020Universal Approximation in Dropout Neural Networkscited by 3
  2. 2021Uncertainty quantification in a mechanical submodel driven by a Wasserstein-GANcited by 2

Built on by

Cited by year (2026 to 14 Oct)

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

2 papers.

  1. 2025A generalized Wasserstein-2 distance approach for efficient reconstruction of random field models using stochastic neural networkscited by 0
  2. 2026A Local Sinkhorn Framework for Conditional Distribution Reconstruction of Multidimensional Random Fieldscited by 0