On a large scale of 42 time series datasets, Chronos demonstrates impressive empirical performance. In the zero-shot setting, it matches or even outperforms many baselines which are trained on the dataset.
TL;DR:<p>* Scale the time series data and quantize the floating point values into B bins.<p>* Each bin becomes a corresponding token id in a vocabulary of B embeddings.<p>* Train a small LLM to predict the next token id given a sequence of token ids.<p>* At each time step, the LLM gives you a probability distribution over B bins.