Chronos: Learning the Language of Time Series

arXiv:2403.07815v1 Announce Type: new
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 …

abstract architectures arxiv cross-entropy cs.ai cs.lg entropy framework language language model loss quantization scaling series simple time series trains transformer type values via