Efficiently Generating Correlated Sample Paths from Multi-step Time Series Foundation Models
cs.LG, stat.ML
Submitted: 2025-10-02
Updated: 2025-10-02
Project page: https://milets18.github.io/papers/milets18_paper_14.pdf
Terminology
Sources
- An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
- From Tables to Time: Extending TabPFN-v2 to Time Series Forecasting
- Deep Generative Quantile-Copula Models for Probabilistic Forecasting
- From Predictions to Decisions: The Importance of Joint Predictive Distributions
- Multivariate Forecasting Evaluation: On Sensitive and Strictly Proper Scoring Rules
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