【时间序列语言】Chronos: Learning the Language of Time Series

Chronos: Learning the Language of Time Series 学习时间序列语言

2024.3.12

论文地址
代码地址

Abstract

We introduce Chronos, a simple yet effective framework for pretrained probabilistic time series models. Chronos tokenizes time series values using scaling and quantization into a fixed vocabulary and trains existing transformer-based language model architectures on these tokenized time series via the cross-entropy loss. We pretrained Chronos models based on the T5 family (ranging from 20M to 710M parameters) on a large collection of publicly available datasets, complemented by a synthetic dataset that we generated via Gaussian processes to improve generalization. In a comprehensive benchmark consisting of 42 datasets, and comprising both classical local models and deep learning methods, we show that Chronos models: (a) significantly outperform other methods on datasets that were part of the training corpus; and (b) have comparable and occasionally superior zero-shot performance on new datasets, relative to methods that were trained specifically on them. Our results demonstrate that Chronos models can leverage time series data from diverse domains to improve zero-shot accuracy on unseen forecasting tasks, positioning pretrained models as a viable tool to greatly simplify forecasting pipelines.

我们介绍了 Chronos，这是一个简单而有效的预训练概率时间序列模型框架。

Chronos 使用缩放和量化技术将时间序列值标记为固定词汇，并通过交叉熵损失在这些标记化的时间序列上训练现有的基于transformer的语言模型架构。

我们在大量公开数据集上预训练了基于 T5 系列的 Chronos 模型（参数范围从 2 千万到 7.1 亿个不等），并通过高斯过程生成了一个合成数据集作为补充，以提高泛化能力。

在一个由 42 个数据集组成、同时包含经典局部模型和深度学习方法的综合基准测试中，我们发现 Chronos 模型：

• （a）在属于训练语料库的数据集上的表现明显优于其他方法；
• （b）在新数据集上，与专门训练过的方法相比，Chronos 模型具有不相上下甚至有时更优越的 zero-shot 性能。

我们的研究结果表明，Chronos 模型可以利用来自不同领域的时间序列数据来提高未见预测任务的 zero-shot 准确率，从而将预训练模型定位为大大简化预测流程的可行工具。