{"ID":2849202,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.24574","arxiv_id":"2510.24574","title":"DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment","abstract":"Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct forecast (DF) approach resorts to minimizing the conditional negative log-likelihood, typically estimated by the mean squared error. However, this estimation proves biased when the label sequence exhibits autocorrelation. In this paper, we propose DistDF, which achieves alignment by minimizing a distributional discrepancy between the conditional distributions of forecast and label sequences. Since such conditional discrepancies are difficult to estimate from finite time-series observations, we introduce a joint-distribution Wasserstein discrepancy for time-series forecasting, which provably upper bounds the conditional discrepancy of interest. The proposed discrepancy is tractable, differentiable, and readily compatible with gradient-based optimization. Extensive experiments show that DistDF improves diverse forecasting models and achieves leading performance. Code is available at https://anonymous.4open.science/r/DistDF-F66B.","short_abstract":"Training time-series forecasting models requires aligning the conditional distribution of model forecasts with that of the label sequence. The standard direct forecast (DF) approach resorts to minimizing the conditional negative log-likelihood, typically estimated by the mean squared error. However, this estimation pro...","url_abs":"https://arxiv.org/abs/2510.24574","url_pdf":"https://arxiv.org/pdf/2510.24574v2","authors":"[\"Hao Wang\",\"Licheng Pan\",\"Yuan Lu\",\"Zhixuan Chu\",\"Xiaoxi Li\",\"Shuting He\",\"Zhichao Chen\",\"Haoxuan Li\",\"Qingsong Wen\",\"Zhouchen Lin\"]","published":"2025-10-28T16:09:59Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","project_urls":"[\"https://anonymous.4open.science/r/DistDF-F66B\"]","has_code":false}