DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting
cs.LG, cs.AI
Submitted: 2026-09-26
Updated: 2026-09-26
Code: https://github.com/wwy155/DiffPTS
Terminology
Sources
- RDIT: Residual-based Diffusion Implicit Models for Probabilistic Time Series Forecasting
- Diffusion Models for Time Series Forecasting: A Survey
- Understanding Diffusion Models: A Unified Perspective
- TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation
- Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks