[2603.03760] Harmonic Dataset Distillation for Time Series Forecasting

Computer Science > Machine Learning arXiv:2603.03760 (cs) [Submitted on 4 Mar 2026] Title:Harmonic Dataset Distillation for Time Series Forecasting Authors:Seungha Hong, Sanghwan Jang, Wonbin Kweon, Suyeon Kim, Gyuseok Lee, Hwanjo Yu View a PDF of the paper titled Harmonic Dataset Distillation for Time Series Forecasting, by Seungha Hong and 5 other authors View PDF HTML (experimental) Abstract:Time Series forecasting (TSF) in the modern era faces significant computational and storage cost challenges due to the massive scale of real-world data. Dataset Distillation (DD), a paradigm that synthesizes a small, compact dataset to achieve training performance comparable to that of the original dataset, has emerged as a promising solution. However, conventional DD methods are not tailored for time series and suffer from architectural overfitting and limited scalability. To address these issues, we propose Harmonic Dataset Distillation for Time Series Forecasting (HDT). HDT decomposes the time series into its sinusoidal basis through the FFT and aligns the core periodic structure by Harmonic Matching. Since this process operates in the frequency domain, all updates during distillation are applied globally without disrupting temporal dependencies of time series. Extensive experiments demonstrate that HDT achieves strong cross-architecture generalization and scalability, validating its practicality for large-scale, real-world applications. Comments: Subjects: Machine Learning (cs.L...