HNGlance

Top Best New Show

Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting

https://github.com/amazon-science/chronos-forecasting

by stellalo • 2 years ago

8 3 2 years ago

GI

Related Stories

Loading related stories...

Comments

3

cs702• 2 years ago

TL;DR:

* Scale the time series data and quantize the floating point values into B bins.

* Each bin becomes a corresponding token id in a vocabulary of B embeddings.

* Train a small LLM to predict the next token id given a sequence of token ids.

* At each time step, the LLM gives you a probability distribution over B bins.

huibin_shen• 2 years ago

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.

sebastianpineda• 2 years ago

this is an amazing contribution for the community!

Source preview

github.com

HNGlance

© 2024-2026 HN Glance. Story content belongs to its original sources.

Privacy
Terms