Variational Augmented Invertible Koopman Autoencoder for probabilistic time series forecasting
cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/ax-ml/jax
Terminology
Sources
- Skillful joint probabilistic weather forecasting from marginals
- NICE: Non-linear Independent Components Estimation
- Averaging Weights Leads to Wider Optima and Better Generalization
- Auto-Encoding Variational Bayes
- Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping
- Differentiable Programming for Differential Equations: A Review
- Latent Autoencoder Ensemble Kalman Filter for Nonlinear Data assimilation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks