RI-Loss: A Learnable Residual-Informed Loss for Time Series Forecasting
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (31) · 26277-26284
DOI: 10.1609/aaai.v40i31.39832 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jieting Wang und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Time series forecasting relies on predicting future values from historical data, yet most state-of-the-art approaches—including transformer and multilayer perceptron-based models—optimize using Mean Squared Error (MSE), which has two fundamental weaknesses: its point-wise error computation fails to capture temporal relationships, and it does not account for inherent noise in the data. To overcome these limitations, we introduce the Residual-Informed Loss (RI-Loss), a novel objective function based on the Hilbert-Schmidt Independence Criterion (HSIC). RI-Loss explicitly models noise structure by enforcing dependence between the residual sequence and a random time series, enabling more robust, noise-aware representations. Theoretically, we derive the first non-asymptotic HSIC bound with explicit double-sample complexity terms, achieving optimal convergence rates through Bernstein-type concentration inequalities and Rademacher complexity analysis. This provides rigorous guarantees for RI-Loss optimization while precisely quantifying kernel space interactions. Empirically, experiments across eight real-world benchmarks and five leading forecasting models demonstrate improvements in predictive performance, validating the effectiveness of our approach.
Zitieren
APA
Wang, J., Shang, X., Li, F., & Peng, F. (2026). RI-Loss: A Learnable Residual-Informed Loss for Time Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, 40(31), 26277-26284. https://doi.org/10.1609/aaai.v40i31.39832
Vancouver
Wang J, Shang X, Li F, Peng F. RI-Loss: A Learnable Residual-Informed Loss for Time Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(31):26277-26284. doi:10.1609/aaai.v40i31.39832
BibTeX
@article{Wang2026,
author = {Wang, Jieting and Shang, Xiaolei and Li, Feijiang and Peng, Furong},
title = {RI-Loss: A Learnable Residual-Informed Loss for Time Series Forecasting},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {31},
pages = {26277--26284},
doi = {10.1609/aaai.v40i31.39832}
}
EUVIMED