Deep Time-series Forecasting Needs Kernelized Moment Balancing

TL;DR

This paper introduces Kernelized Moment Balancing for deep time-series forecasting, which adaptively matches distribution moments to improve accuracy and achieve state-of-the-art results.

Contribution

It proposes a novel distribution balancing objective using RKHS to adaptively select informative moments, addressing limitations of existing methods.

Findings

KMB-DF improves forecasting accuracy across datasets.

It achieves state-of-the-art performance.

The method integrates seamlessly with gradient-based training.

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.