针对非平稳时间序列，提出轻量级测试时自适应方法，提升模型在数据漂移下的预测稳定性。
Test-Time Adaptation for Non-stationary Time Series: From Synthetic Regime Shifts to Financial Markets
- 冻结主干网络，仅更新归一化参数，利用近期无标签窗口自适应调整
- 在金融数据上，简单批量归一化更新即有效，激进调整反而降低性能
- 适用于金融、经济等动态变化强的场景，特别适合资源受限部署
实际时间序列往往非平稳。当数据分布发生变化时，基于历史数据训练的预测模型会失准。本文研究一种小规模测试时自适应（TTA）框架，用于因果时间序列预测与方向分类。主干模型冻结，仅通过近期无标签窗口更新归一化仿射参数。分类任务中最小化熵并强制时间一致性；回归任务中最小化弱时间保持增强下的预测方差，并可选地从指数移动平均教师模型蒸馏。引入二次漂移惩罚和不确定性触发回退机制以保证更新稳定。在两阶段评估中：首先在ETT基准上测试合成制度转换，其次在疫情、高通胀与复苏阶段的每日股票（SPY、QQQ）与外汇（EUR/USD）序列上验证。在合成渐变漂移下，基于归一化的TTA能降低预测误差；而在真实金融市场中，仅更新批量归一化统计量已是稳健默认方案，更激进的归一化自适应反而损害性能。结果为在非平稳时间序列上部署TTA提供了实用指导。
原文摘要 · Abstract (English)
Time series encountered in practice are rarely stationary. When the data distribution changes, a forecasting model trained on past observations can lose accuracy. We study a small-footprint test-time adaptation (TTA) framework for causal timeseries forecasting and direction classification. The backbone is frozen, and only normalization affine parameters are updated using recent unlabeled windows. For classification we minimize entropy and enforce temporal consistency; for regression we minimize prediction variance across weak time-preserving augmentations and optionally distill from an EMA teacher. A quadratic drift penalty and an uncertainty triggered fallback keep updates stable. We evaluate this framework in two stages: synthetic regime shifts on ETT benchmarks, and daily equity and FX series (SPY, QQQ, EUR/USD) across pandemic, high-inflation, and recovery regimes. On synthetic gradual drift, normalization-based TTA improves forecasting error, while in financial markets a simple batch-normalization statistics update is a robust default and more aggressive norm-only adaptation can even hurt. Our results provide practical guidance for deploying TTA on non-stationary time series.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。