mlsanityData to 14 Oct 2026

Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Data

arXiv 2208.12975 ↗First posted 27 Aug 2022cs.LG stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

This work proposes a Stochastic Variational Deep Kernel Learning method for the data-driven discovery of low-dimensional dynamical models from high-dimensional noisy data. The framework is composed of an encoder that compresses high-dimensional measurements into low-dimensional state variables, and a latent dynamical model for the state variables that predicts the system evolution over time. The training of the proposed model is carried out in an unsupervised manner, i.e., not relying on labeled data. Our learning method is evaluated on the motion of a pendulum -- a well studied baseline for nonlinear model identification and control with continuous states and control inputs -- measured via high-dimensional noisy RGB images. Results show that the method can effectively denoise measurements, learn compact state representations and latent dynamical models, as well as identify and quantify modeling uncertainties.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 24 of its 54 references that are in the map. First posted on arXiv 27 Aug 2022.

Builds on

24 of 54 references.

References · 24

  1. 2016OpenAI Gymcited by 1,736
  2. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  3. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  4. 2020Mastering Atari with Discrete World Modelscited by 1,007
  5. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  6. 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 609
  7. 2015Deep Kernel Learningcited by 445
  8. 2015Deep Kalman Filterscited by 166
  9. 2016Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Datacited by 156
  10. 2021Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and controlcited by 137
  11. 2014Dynamic mode decomposition with controlcited by 129
  12. 2018State Representation Learning for Control: An Overviewcited by 127
12 more
  1. 2017A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learningcited by 107
  2. 2016Stochastic Variational Deep Kernel Learningcited by 93
  3. 2021The Promises and Pitfalls of Deep Kernel Learningcited by 81
  4. 2014Manifold Gaussian Processes for Regressioncited by 80
  5. 2018Probabilistic Recurrent State-Space Modelscited by 64
  6. 2017Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networkscited by 48
  7. 2018Learning and Querying Fast Generative Models for Reinforcement Learningcited by 48
  8. 2015From Pixels to Torques: Policy Learning with Deep Dynamical Modelscited by 45
  9. 2022Bayesian operator inference for data-driven reduced-order modelingcited by 19
  10. 2019Adaptive Deep Kernel Learningcited by 15
  11. 2014Learning deep dynamical models from image pixelscited by 7
  12. 2015Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Modelscited by 6

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 2.

6 papers.

  1. 2023Multi-fidelity reduced-order surrogate modelingcited by 18
  2. 2024VENI, VINDy, VICI: a generative reduced-order modeling framework with uncertainty quantificationcited by 9
  3. 2023Gaussian process learning of nonlinear dynamicscited by 5
  4. 2024Recurrent Deep Kernel Learning of Dynamical Systemscited by 1
  5. 2025Towards scientific machine learning for granular material simulations -- challenges and opportunitiescited by 1
  6. 2025Multi-Fidelity Delayed Acceptance: hierarchical MCMC sampling for Bayesian inverse problems combining multiple solvers through deep neural networkscited by 1