arXiv：cs.AI· Federico Zucchi, Yi Xie, Chao Zhang, Thomas Lampert, Ziyue Li·· 5 小时前
自适应分块对时间序列预测并非易事：与调优均匀分块基线对比研究
Adaptive Patching Is Harder Than It Looks For Time-Series Forecasting
AI 导读
研究对比了三种自适应分块方法与调优后的均匀分块基线，保持相同骨干网络和训练协议，发现在长时程基准上两者准确率差异普遍较小，自适应分块并无一致优势，均匀方案训练更快且推理时无需自适应路由。作者为此提出预算化分块分配的理论框架，推导出非均匀分配在同预算下优于均匀分配的精确条件。
正文
Abstract:Adaptive patching has been proposed for time-series forecasting: allocate finer patches where the sequence looks locally informative. We compare three adaptive patching methods with tuned uniform counterparts that use one fixed patch size throughout the input, while preserving each method's backbone family and shared training protocol. Across the evaluated long-horizon benchmarks, we observe mostly small accuracy differences and no consistent advantage for adaptive patching; uniform variants generally train faster and avoid adaptive routing at inference. Motivated by these observations, we develop a theoretical framework for budgeted patch allocation through a common resolution-density representation of uniform, nonuniform, and overlapping layouts, independently of the patching rule. Within a separable shared-loss model, we derive an exact criterion for when nonuniform allocation improves on uniform allocation at the same budget. We characterize modeled gains locally through a quadratic surrogate and bound them globally under strong convexity and a bounded loss derivative. The analysis distinguishes where resolution is placed from how much it is redistributed: even an allocation that correctly ranks regions by their weights can redistribute too much resolution and increase modeled loss. Without coupling across time, positive regional weights preserve the minimizers of the shared loss. When the shared loss has a common minimizing rate, the remaining absolute headroom for improvement tends to zero as the uniform rate approaches it. These results characterize the roles of regional weighting, placement, and redistribution strength under the stated model. The empirical findings support evaluating adaptive patching against a tuned uniform baseline and weighing any accuracy gain against the additional training and inference cost of adaptive routing.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Information Theory (cs.IT) |
| Cite as: | arXiv:2606.04074 [cs.LG] |
| (or arXiv:2606.04074v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2606.04074 arXiv-issued DOI via DataCite |
Submission history
From: Federico Zucchi [view email]
[v1]
Tue, 2 Jun 2026 15:49:06 UTC (165 KB)
[v2]
Tue, 13 Oct 2026 15:00:00 UTC (745 KB)
来源：arXiv：cs.AI · arxiv.org