arXiv：cs.LG· Lorena Egger, Mathis Linger·· 4 小时前AI 评分25
StaFIR：平稳性感知因果滤波器的凸学习
StaFIR: Convex Learning of Stationarity-Aware Causal Filters
AI 导读
研究者提出 StaFIR，一种因果有限脉冲响应滤波器，通过非负指数滞后轮廓混合与凸学习目标，在经验平稳性与输入相似度之间取得平衡。在 ARFIMA–GARCH 和滚动金融序列（含已实现波动率预测）上，StaFIR 能随持久性调整滤波强度，并在平稳区间限制不必要的变换。下游预测精度与固定半阶差分无明显差异，但对原始信号的相似度更高；直接预测实验显示输入相似度越高，预测损失越小。
正文
Abstract:Reducing nonstationarity in a persistent time series entails deciding how much of its temporal dependence to remove. In finance, fractional differencing is often tuned using the Augmented Dickey--Fuller (ADF) test, limiting the search to a one-parameter family of lag profiles and addressing input preservation only indirectly. We propose StaFIR, a causal finite-impulse-response filter with a learned nonnegative mixture of exponential lag profiles. Its convex learning objective balances empirical stationarity with similarity to the input. We evaluate StaFIR on ARFIMA--GARCH controlled settings and rolling financial series, including a realized-volatility forecasting task. The experiments show that StaFIR adjusts its filtering strength to persistence while limiting unnecessary transformation in stationary regimes. In downstream forecasting, there is no clear accuracy difference from fixed half-order differencing, while StaFIR achieves higher measured similarity to the raw signal. A complementary direct forecasting experiment finds that greater input similarity is associated with smaller forecasting penalties, although the raw representation remains stronger.
| Comments: | Accepted at the TS-LIMITS Workshop at NeurIPS 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.07430 [cs.LG] |
| (or arXiv:2610.07430v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07430 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lorena Egger [view email]
[v1]
Mon, 5 Oct 2026 21:37:41 UTC (159 KB)
来源：arXiv：cs.LG · arxiv.org