Deep Time-series Forecasting Needs Kernelized Moment Balancing

• URL: http://arxiv.org/abs/2602.00717v1
• Date: Sat, 31 Jan 2026 13:20:18 GMT
• Title: Deep Time-series Forecasting Needs Kernelized Moment Balancing
• Authors: Licheng Pan, Hao Wang, Haocheng Yang, Yuqi Li, Qingsong Wen, Xiaoxi Li, Zhichao Chen, Haoxuan Li, Zhixuan Chu, Yuan Lu,
• Abstract summary: Deep time-series forecasting can be formulated as a distribution balancing problem aimed at aligning the distribution of the forecasts and ground truths.<n>We propose direct forecasting with kernelized moment balancing (KMB-DF)<n>Experiments across multiple models and datasets show that KMB-DF consistently improves forecasting accuracy and achieves state-of-the-art performance.
• Score: 56.619037429652984
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep time-series forecasting can be formulated as a distribution balancing problem aimed at aligning the distribution of the forecasts and ground truths. According to Imbens' criterion, true distribution balance requires matching the first moments with respect to any balancing function. We demonstrate that existing objectives fail to meet this criterion, as they enforce moment matching only for one or two predefined balancing functions, thus failing to achieve full distribution balance. To address this limitation, we propose direct forecasting with kernelized moment balancing (KMB-DF). Unlike existing objectives, KMB-DF adaptively selects the most informative balancing functions from a reproducing kernel hilbert space (RKHS) to enforce sufficient distribution balancing. We derive a tractable and differentiable objective that enables efficient estimation from empirical samples and seamless integration into gradient-based training pipelines. Extensive experiments across multiple models and datasets show that KMB-DF consistently improves forecasting accuracy and achieves state-of-the-art performance. Code is available at https://anonymous.4open.science/r/KMB-DF-403C.

Related papers

• Analytic Incremental Learning For Sound Source Localization With Imbalance Rectification [15.161051314343105]
  Sound source localization (SSL) demonstrates remarkable results in controlled settings but struggles in real-world deployment.<n>We propose a unified framework with two key innovations to mitigate these issues.<n>On the SSLR benchmark, our proposal achieves state-of-the-art (SoTA) results of 89.0% accuracy, 5.3 mean absolute error, and 1.6 backward transfer robustness.
  arXiv  Detail & Related papers  (2026-01-26T10:22:01Z)
• SimDiff: Simpler Yet Better Diffusion Model for Time Series Point Forecasting [8.141505251306622]
  Diffusion models have recently shown promise in time series forecasting.<n>They often fail to achieve state-of-the-art point estimation performance.<n>We propose SimDiff, a single-stage, end-to-end framework for point estimation.
  arXiv  Detail & Related papers  (2025-11-24T16:09:55Z)
• DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment [92.70019102733453]
  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.
  arXiv  Detail & Related papers  (2025-10-28T16:09:59Z)
• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional dependencies for general score-mismatched diffusion samplers.<n>We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions.<n>This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise [51.87307904567702]
  Quantile regression is a leading approach for obtaining such intervals via the empirical estimation of quantiles in the distribution of outputs.<n>We propose Relaxed Quantile Regression (RQR), a direct alternative to quantile regression based interval construction that removes this arbitrary constraint.<n>We demonstrate that this added flexibility results in intervals with an improvement in desirable qualities.
  arXiv  Detail & Related papers  (2024-06-05T13:36:38Z)
• Debiased Collaborative Filtering with Kernel-Based Causal Balancing [28.89858891537214]
  We propose an algorithm that adaptively balances the kernel function and theoretically analyze the generalization error bound of our methods. We conduct extensive experiments to demonstrate the effectiveness of our methods.
  arXiv  Detail & Related papers  (2024-04-30T14:43:51Z)
• Distributional Gradient Boosting Machines [77.34726150561087]
  Our framework is based on XGBoost and LightGBM. We show that our framework achieves state-of-the-art forecast accuracy.
  arXiv  Detail & Related papers  (2022-04-02T06:32:19Z)
• CRPS Learning [0.0]
  Combination and aggregation techniques can improve forecast accuracy substantially. We discuss pointwise online aggregation algorithms that optimize with respect to the continuous ranked probability score (CRPS)
  arXiv  Detail & Related papers  (2021-02-01T16:54:05Z)
• Probabilistic electric load forecasting through Bayesian Mixture Density Networks [70.50488907591463]
  Probabilistic load forecasting (PLF) is a key component in the extended tool-chain required for efficient management of smart energy grids. We propose a novel PLF approach, framed on Bayesian Mixture Density Networks. To achieve reliable and computationally scalable estimators of the posterior distributions, both Mean Field variational inference and deep ensembles are integrated.
  arXiv  Detail & Related papers  (2020-12-23T16:21:34Z)

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.