时间序列基础模型的潜在推理时引导
Latent Inference-Time Guidance of Time Series Foundation Models
- Sorbonne Université（索邦大学）
- EDF R&D（法国电力公司研发部）
- UCL（伦敦大学学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出潜在推理时引导方法，通过时间相关潜在空间自适应集成多个时间序列基础模型的预测，兼顾可辨识性与重构保证，实验证明其与传统集成方法竞争力相当。
AI中文摘要：
时间序列基础模型（TSFMs）目前在预测任务中提供了最先进的结果。它们开箱即用，并依赖上下文学习来进行预测，这使得其性能质量对用户选择的回看窗口、协变量、预测范围及训练数据分布高度敏感。在实践中，预测质量各不相同但具有互补性，这凸显了对一种有原则的集成方法的需求，而非选择最佳上下文。本文引入了时间序列基础模型的潜在推理时引导，该方法通过具有独立分量的时间相关潜在空间自适应地组合一组TSFM预测。该框架具备可辨识性和重构保证，同时保持了基础模型的现成可用特性。我们在不同频率和多个领域的数据集上进行了实验：结果表明，该方法与传统集成方法具有竞争力。
英文摘要：
Time Series Foundation Models (TSFMs) currently provide state-of-the-art results in forecasting tasks. They are available out-of-the-box and rely on in-context learning to make their predictions, which makes the quality of their performance highly sensitive to the user-selected lookback, covariates, horizon and training data distributions. In practise, the quality of the forecasts are variable but complementary, which highlights the need for a principled ensembling approach, rather than selecting the best context. This paper introduces Latent Inference-Time Guidance for TSFMs, which adaptively combines a pool of TSFM forecasts through a time-dependent latent space with independent components. The framework comes equipped with identifiability and reconstruction guarantees, whilst maintaining the off-the-shelf aspect of foundation models. We provide experiments on datasets at various frequencies and from multiple domains: these show that the approach is competitive with traditional ensembling approaches.
