mlsanityData to 7 Oct 2026

Variational Augmented Invertible Koopman Autoencoder for probabilistic time series forecasting

arXiv 2609.37435 ↗First posted 29 Sep 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Neural Koopman autoencoder models have been shown to successfully build a latent embedding with linear dynamics for arbitrary dynamical systems, enabling strong performance in long-term time series forecasting. However, these models usually work in a deterministic setting, which does not allow the quantification of the uncertainty of their predictions. Thus, we propose the new Variational Augmented Invertible Koopman AutoEncoder (VAIKAE), in which the latent embedding follows a Gaussian distribution instead of being deterministic. A key property of the VAIKAE architecture is that it leverages normalizing flow models, enabling the use of likelihood computations in the state space of dynamical systems for training a model. We further propose new strategies for uncertainty-aware latent data assimilation with a trained VAIKAE model. The effectiveness of our methods is demonstrated in a series of experiments on long-term time series forecasting benchmarks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 52 of its 90 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

52 of 90 references.

References · 52

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2016Density estimation using Real NVPcited by 2,029
  8. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  9. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  10. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  11. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  12. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
38 more
  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  2. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  3. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  4. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 577
  5. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 491
  6. 2021Machine learning accelerated computational fluid dynamicscited by 461
  7. 2018Conditional Neural Processescited by 421
  8. 2022Non-stationary Transformers: Exploring the Stationarity in Time Series Forecastingcited by 385
  9. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
  10. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 332
  11. 2021Modern Koopman Theory for Dynamical Systemscited by 269
  12. 2017Linearly-Recurrent Autoencoder Networks for Learning Dynamicscited by 142
  13. 2022On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networkscited by 119
  14. 2020Forecasting Sequential Data using Consistent Koopman Autoencoderscited by 114
  15. 2023Non-autoregressive Conditional Diffusion Models for Time Series Predictioncited by 77
  16. 2023Machine learning with data assimilation and uncertainty quantification for dynamical systems: a reviewcited by 74
  17. 2017On Convergence of Extended Dynamic Mode Decomposition to the Koopman Operatorcited by 70
  18. 2019Learning Compositional Koopman Operators for Model-Based Controlcited by 67
  19. 2019Reliable training and estimation of variance networkscited by 63
  20. 2019Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stabilitycited by 53
  21. 2025Skillful joint probabilistic weather forecasting from marginalscited by 53
  22. 2023Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEscited by 48
  23. 2024ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Predictioncited by 40
  24. 2024Generative Artificial Intelligence: A Systematic Review and Applicationscited by 37
  25. 2021Latent Space Data Assimilation by using Deep Learningcited by 29
  26. 2021Constructing Neural Network-Based Models for Simulating Dynamical Systemscited by 29
  27. 2024Probabilistic Weather Forecasting with Hierarchical Graph Neural Networkscited by 29
  28. 2022Differentiable Programming for Earth System Modelingcited by 21
  29. 2024Differentiable Programming for Differential Equations: A Reviewcited by 21
  30. 2024Temporally Consistent Koopman Autoencoders for Forecasting Dynamical Systemscited by 15
  31. 2023Koopman operator learning using invertible neural networkscited by 12
  32. 2023Neural Koopman prior for data assimilationcited by 9
  33. 2024Learning Hamiltonian neural Koopman operator and simultaneously sustaining and discovering conservation lawcited by 7
  34. 2025Ensemble Kalman filter in latent space using a variational autoencoder paircited by 5
  35. 2021Deep Probabilistic Koopman: Long-term time-series forecasting under periodic uncertaintiescited by 4
  36. 2025Augmented Invertible Koopman Autoencoder for long-term time series forecastingcited by 3
  37. 2026Latent Autoencoder Ensemble Kalman Filter for Nonlinear Data assimilationcited by 3
  38. 2024Koopman Ensembles for Probabilistic Time Series Forecastingcited by 1

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.