Chronos (pretrained model)
Chronos is a framework for pretrained probabilistic time series models developed in 2024 by Amazon Web Services researchers.[1] By tokenizing time series values through scaling and quantization into a fixed vocabulary, Chronos utilizes existing transformer-based language model architectures, specifically training them via cross-entropy loss. The model variations within the Chronos family are based on the T5 family, with sizes ranging from 20 million to 710 million parameters.[citation needed]
Development[edit]
Chronos was pretrained on a broad array of publicly available datasets, alongside a synthetic dataset created through Gaussian processes to enhance its ability to generalize across different tasks. This approach allowed Chronos to undergo comprehensive pretraining, preparing it for a wide range of forecasting applications.
Performance[edit]
In an extensive benchmark covering 42 datasets—which included both traditional local models and modern deep learning approaches—Chronos demonstrated notable achievements:
Training Corpus Performance: On datasets included in its training corpus, Chronos models significantly outperformed competing methods.
Zero-Shot Performance: When tested on new datasets, without specific training, Chronos displayed comparable or occasionally superior performance relative to models that were trained on those specific datasets.
Impact[edit]
The results from various benchmarks highlight Chronos's capability to leverage time series data from diverse domains. This enables it to improve zero-shot accuracy on unseen forecasting tasks markedly. The introduction and success of Chronos models mark a significant step forward, suggesting that pretrained models can serve as effective and simplified solutions in forecasting pipelines across a range of fields.
References[edit]
- ↑ Ganaie, Muhammad Athar (2024-03-15). "Amazon AI Researchers Introduce Chronos: A New Machine Learning Framework for Pretrained Probabilistic Time Series Models". MarkTechPost. Retrieved 2024-03-22.
This article "Chronos (pretrained model)" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Chronos (pretrained model). Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.
