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

• URL: http://arxiv.org/abs/2510.24574v1
• Date: Tue, 28 Oct 2025 16:09:59 GMT
• Title: DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment
• Authors: Hao Wang, Licheng Pan, Yuan Lu, Zhixuan Chu, Xiaoxi Li, Shuting He, Zhichao Chen, Haoxuan Li, Qingsong Wen, Zhouchen Lin,
• Abstract summary: Training time-series forecast models requires aligning the conditional distribution of model forecasts with that of the label sequence.<n>We propose DistDF, which achieves alignment by alternatively minimizing a discrepancy between the conditional forecast and label distributions.
• Score: 92.70019102733453
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training time-series forecast models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct forecast (DF) approach resorts to minimize the conditional negative log-likelihood of the label sequence, typically estimated using the mean squared error. However, this estimation proves to be biased in the presence of label autocorrelation. In this paper, we propose DistDF, which achieves alignment by alternatively minimizing a discrepancy between the conditional forecast and label distributions. Because conditional discrepancies are difficult to estimate from finite time-series observations, we introduce a newly proposed joint-distribution Wasserstein discrepancy for time-series forecasting, which provably upper bounds the conditional discrepancy of interest. This discrepancy admits tractable, differentiable estimation from empirical samples and integrates seamlessly with gradient-based training. Extensive experiments show that DistDF improves the performance diverse forecast models and achieves the state-of-the-art forecasting performance. Code is available at https://anonymous.4open.science/r/DistDF-F66B.

Related papers

• Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraints [5.539946449743145]
  We introduce a constrained sampling framework that enforces hard constraints, such as physical laws or observational consistency, at generation time.<n>Our approach defines a constrained forward process that diffuses only over the feasible set of constraint-satisfying samples, inducing constrained marginal distributions.<n>We propose Predict-Project-Renoise (PPR), an iterative algorithm that samples from the constrained marginals by alternating between denoising predictions, projecting onto the feasible set, and renoising.
  arXiv  Detail & Related papers  (2026-01-28T20:50:19Z)
• ResCP: Reservoir Conformal Prediction for Time Series Forecasting [39.81023599249223]
  Conformal prediction offers a powerful framework for building distribution-free prediction intervals for exchangeable data.<n>We propose Reservoir Conformal Prediction (ResCP), a novel training-free conformal prediction method for time series.
  arXiv  Detail & Related papers  (2025-10-06T17:37:44Z)
• RDIT: Residual-based Diffusion Implicit Models for Probabilistic Time Series Forecasting [4.140149411004857]
  RDIT is a plug-and-play framework that combines point estimation and residual-based conditional diffusion with a bidirectional Mamba network.<n>We show that RDIT achieves lower CRPS, rapid inference, and improved coverage compared to strong baselines.
  arXiv  Detail & Related papers  (2025-09-02T14:06:29Z)
• Bridging the Last Mile of Prediction: Enhancing Time Series Forecasting with Conditional Guided Flow Matching [9.465542901469815]
  Conditional Guided Flow Matching (CGFM) is a model-agnostic framework that extends flow matching by integrating outputs from an auxiliary predictive model.<n>CGFM incorporates historical data as both conditions and guidance, uses two-sided conditional paths, and employs affine paths to expand the path space.<n> Experiments across datasets and baselines show CGFM consistently outperforms state-of-the-art models, advancing forecasting.
  arXiv  Detail & Related papers  (2025-07-09T18:03:31Z)
• FreDF: Learning to Forecast in the Frequency Domain [54.2091536822376]
  Time series modeling presents unique challenges due to autocorrelation in both historical data and future sequences.<n>We propose the Frequency-enhanced Direct Forecast (FreDF) which mitigates label autocorrelation by learning to forecast in the frequency domain.
  arXiv  Detail & Related papers  (2024-02-04T08:23:41Z)
• Attention-Based Ensemble Pooling for Time Series Forecasting [55.2480439325792]
  We propose a method for pooling that performs a weighted average over candidate model forecasts. We test this method on two time-series forecasting problems: multi-step forecasting of the dynamics of the non-stationary Lorenz 63 equation, and one-step forecasting of the weekly incident deaths due to COVID-19.
  arXiv  Detail & Related papers  (2023-10-24T22:59:56Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2023-10-17T20:30:16Z)
• When Rigidity Hurts: Soft Consistency Regularization for Probabilistic Hierarchical Time Series Forecasting [69.30930115236228]
  Probabilistic hierarchical time-series forecasting is an important variant of time-series forecasting. Most methods focus on point predictions and do not provide well-calibrated probabilistic forecasts distributions. We propose PROFHiT, a fully probabilistic hierarchical forecasting model that jointly models forecast distribution of entire hierarchy.
  arXiv  Detail & Related papers  (2022-06-16T06:13:53Z)
• Training on Test Data with Bayesian Adaptation for Covariate Shift [96.3250517412545]
  Deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. We derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters. We show that our method improves both accuracy and uncertainty estimation.
  arXiv  Detail & Related papers  (2021-09-27T01:09:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.