DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment

arXiv:2510.24574 · cs.LG, cs.AI · Submitted 2025-10-28 · Read on arXiv

cs.LG, cs.AI

Submitted: 2025-10-28

Updated: 2026-10-06

Comments: Accepted by ICLR 2026

Journal ref: ICLR 2026

Code: https://github.com/Master-PLC/DistDF

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 2× in this paper · explained in 1 episode

Sources

• FinTSB: A Comprehensive and Practical Benchmark for Financial Time Series Forecasting
• To See Far, Look Close: Evolutionary Forecasting for Long-term Time Series
• DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables
• Deep Time Series Models: A Comprehensive Survey and Benchmark

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