通过多样化采样提升时间序列模型推理性能，无需重训练。
Diversified Scaling Inference in Time Series Foundation Models
- 用时序扰动增强采样多样性，拓展生成分布支持范围。
- 发现多样化采样在超过临界样本量时优于标准采样。
- 适合追求高效推理优化的工业级时间序列建模应用。
时间序列基础模型（TSFMs）的发展主要依赖大规模预训练，但推理阶段的计算潜力仍被忽视。本文系统研究两个问题：标准采样推理下的TSFMs行为特征，以及可控采样多样性是否能提升性能。实验表明，标准采样常因解空间探索不足而违背缩放定律。为此，我们引入基于定制化时序扰动的多样化推理缩放，理论上分析了多样性与保真度的权衡关系，并推导出多样化采样超越标准采样的临界样本阈值。在多种TSFMs和数据集上的大量实验显示，合理设计的多样化推理可显著提升性能，且无需参数更新，确立推理设计为关键、高效的优化维度。作为应用，提出RobustMSE，用于在固定预算下量化TSFM的性能冗余空间。整体成果揭示了各因素交互机制，实现无需重训练的大规模并行推理优化。
原文摘要 · Abstract (English)
The advancement of Time Series Foundation Models (TSFMs) has been driven primarily by large-scale pre-training, but inference-time compute potential remains largely untapped. This work systematically investigates two questions: how do TSFMs behave under standard sampling-based inference scaling, and can controlled sampling diversity enhance performance? We first examine the properties of TSFMs under standard sampling often fail to adhere to scaling laws due to insufficient exploration of the solution space. Building on this, we then delve into diversified inference scaling via tailored time series perturbations to expand the generative distribution's support. We theoretically analyze the diversity-fidelity trade-off and derive a critical sample threshold for diversified sampling to outperform standard sampling. Extensive experiments across various TSFMs and datasets show proper diversified inference scaling yields substantial performance gains without parameter updates, establishing inference design as a critical, compute-efficient dimension of TSFM optimization. As an application, we propose RobustMSE, a rigorous metric to quantify the headroom performance of TSFM under a fixed budget. Overall, our findings clarify these factor interactions, enabling reliable performance via diverse large-scale inference time series in parallel environments without re-training TSFMs.
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。