Variational Augmented Invertible Koopman Autoencoder for probabilistic time series forecasting
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
The Flow has not summarised this story yet — read it at arXiv Machine Learning.
TORNADO is a latent probabilistic forecasting framework for partial differential equations that models next-step prediction as stochastic transport between VAE encoder posteriors. It learns a state-dependent stochastic differential equation, allowing predictive uncertainty to adapt to local latent dynamics rather than relying on fixed global stochasticity. The model is trained with analytic conditional endpoint targets and an energy distance regularizer, achieving better uncertainty calibration than several generative baselines while maintaining comparable predictive accuracy.
arXiv:2602.02832v4 Announce Type: replace Abstract: Forward forecasting and data assimilation are the two important aspects in physical simulation: one propagates the state forward, the other recover...
The paper introduces the Diffusion-Driven State Space Model (DDSSM), which replaces the Gaussian transition distribution in deep state space models with a diffusion model. This approach addresses the trade‑off between accurate forecasting and faithful capture of latent dynamics by enabling joint training of an autoencoder and a diffusion model on sequential data. Experiments show that DDSSM outperforms a state‑of‑the‑art deep SSM in fitting and forecasting a simulated time series with multimodal transitions.
The paper introduces prequential posteriors, a Bayesian approach that uses a predictive‑sequential loss function to update deep generative forecasting models (DGFMs) when new data arrive. By adopting a consistency notion suitable for model misspecification, the authors prove that both the loss minimizer and the posterior concentrate on parameters with optimal predictive performance. Scalable inference is achieved with parallelisable waste‑free sequential Monte Carlo samplers that employ preconditioned gradient kernels, and the method is validated on synthetic and real meteorological time‑series data.
The paper presents PAC‑Bayesian reconstruction guarantees for Variational Autoencoders applied to time‑series data. It extends existing bounds, which were limited to i.i.d. settings, to Markovian latent structures, allowing temporal dependencies to be captured without the bounds growing with trajectory length. The authors also provide an example framework showing that the required assumptions are not overly restrictive.
arXiv:2507. 23615v2 Announce Type: replace-cross Abstract: Data augmentation is becoming increasingly important across various areas of time series analysis, including forecasting, classification, and anomaly detection.