arXiv Machine Learning

Variational Augmented Invertible Koopman Autoencoder for probabilistic time series forecasting

arXiv Machine Learning
6d ago

TORNADO: Adaptive Latent Stochastic Transport for Calibrated Probabilistic PDE Forecasting

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.

By Jorge Mifsut-Benet, Armand Kassa\"i Koupa\"i, Ramon Daniel Regueiro-Espino, Nicolas Baskiotis, Patrick Gallinari
arXiv Machine Learning
Nov 6

Diffusion-Driven State Space Models

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.

By Jack Ruder, Michael Wojnowicz
arXiv Machine Learning
Aug 31

Prequential posteriors

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.

By Shreya Sinha-Roy, Richard G. Everitt, Christian P. Robert, Ritabrata Dutta
arXiv Machine Learning
Sep 7

PAC-Bayesian Reconstruction Guarantees for Time Series Variational Autoencoders

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.

By Chlo\'e Hashimoto-Cullen, Ghislain Agoua, Benjamin Guedj, Sylvain Le Corff
arXiv Machine Learning
Sep 16

Stable by Construction: Variational Latent Markov Operators for Long-Horizon PDE Prediction

The paper introduces a variational framework called VAMO that incorporates latent Markov dynamics for neural PDE solvers, aiming to improve long‑horizon predictions by mitigating error accumulation. By representing physical states as latent distributions and evolving them through probabilistic transitions, the method aligns learned dynamics with a spectral geometry induced by structured Gaussian perturbations. Experiments on fluid‑dynamics benchmarks show that VAMO reduces error growth and enhances rollout stability compared to deterministic and noise‑injection baselines.

By Junyi Liao, Johann Guilleminot, Vahid Tarokh
arXiv AI
Sep 17

Principled Koopman Representations with Kalman Inference for Efficient Time-Series Prediction

The paper introduces K$^2$SVD, a method that learns the leading singular functions of the Koopman operator by optimizing a Hilbert-Schmidt objective, producing a low‑rank, interpretable Koopman representation with a compact latent space. In this space, temporal evolution is modeled with a linear Gaussian state‑space model and inference is performed via Kalman filtering to reduce noise accumulation in multi‑step predictions. Experiments demonstrate that K$^2$SVD outperforms state‑of‑the‑art methods on multiple datasets, achieving faster prediction speeds and lower computational cost.

By Ruiquan Li, Yuheng Bu
Hugging Face Trending Papers
Oct 13

Deterministic Prediction as Global Velocity: Flow Matching for Probabilistic Time-Series Forecast

The paper introduces DV-Flow, a flow‑matching framework that treats deterministic prediction as a parallel velocity component instead of embedding it within the generative process. This design stabilizes end‑to‑end training and unifies several existing methods as special cases, enabling direct comparison. Experiments on six real‑world datasets show that DV‑Flow consistently outperforms strong baselines in probabilistic time‑series forecasting.