mlsanityData to 13 Oct 2026

Learning Dynamical Systems from Noisy Sensor Measurements using Multiple Shooting

arXiv 2106.11712 ↗First posted 22 Jun 2021cs.LG stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

Modeling dynamical systems plays a crucial role in capturing and understanding complex physical phenomena. When physical models are not sufficiently accurate or hardly describable by analytical formulas, one can use generic function approximators such as neural networks to capture the system dynamics directly from sensor measurements. As for now, current methods to learn the parameters of these neural networks are highly sensitive to the inherent instability of most dynamical systems of interest, which in turn prevents the study of very long sequences. In this work, we introduce a generic and scalable method based on multiple shooting to learn latent representations of indirectly observed dynamical systems. We achieve state-of-the-art performances on systems observed directly from raw images. Further, we demonstrate that our method is robust to noisy measurements and can handle complex dynamical systems, such as chaotic ones.

Key facts. Cited by 6 papers in the map (data through 13 Oct 2026). Builds on 24 of its 47 references that are in the map. First posted on arXiv 22 Jun 2021.

Builds on

24 of 47 references.

References · 24

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,223
  2. 2016Layer Normalizationcited by 5,624
  3. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,432
  4. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  5. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 754
  6. 2017MoCoGAN: Decomposing Motion and Content for Video Generationcited by 524
  7. 2015Unsupervised Learning of Video Representations using LSTMscited by 435
  8. 2015Deep multi-scale video prediction beyond mean square errorcited by 300
  9. 2016Unsupervised Learning for Physical Interaction through Video Predictioncited by 259
  10. 2017Stochastic Variational Video Predictioncited by 234
  11. 2020Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Predictioncited by 194
  12. 2016Structured Inference Networks for Nonlinear State Space Modelscited by 182
12 more
  1. 2018Stochastic Adversarial Video Predictioncited by 173
  2. 2015Deep Kalman Filterscited by 165
  3. 2016Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Datacited by 154
  4. 2018Learning to Decompose and Disentangle Representations for Video Predictioncited by 121
  5. 2016Video Pixel Networkscited by 108
  6. 2017A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learningcited by 107
  7. 2017Variational Sequential Monte Carlocited by 94
  8. 2019Unsupervised Learning of Object Structure and Dynamics from Videoscited by 92
  9. 2019Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spacescited by 66
  10. 2019Learning interpretable continuous-time models of latent stochastic dynamical systemscited by 30
  11. 2019On the smoothness of nonlinear system identificationcited by 17
  12. 2019Curious iLQR: Resolving Uncertainty in Model-based RLcited by 11

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1; 2024: 3.

6 papers.

  1. 2024Out-of-Domain Generalization in Dynamical Systems Reconstructioncited by 33
  2. 2022Latent Neural ODEs with Sparse Bayesian Multiple Shootingcited by 17
  3. 2022Integrating Multimodal Data for Joint Generative Modeling of Complex Dynamicscited by 14
  4. 2023Learning Space-Time Continuous Neural PDEs from Partially Observed Statescited by 3
  5. 2024LINOCS: Lookahead Inference of Networked Operators for Continuous Stabilitycited by 1
  6. 2024Divide And Conquer: Learning Chaotic Dynamical Systems With Multistep Penalty Neural Ordinary Differential Equationscited by 1