Published:
This article reduces the dimensionality of high-dimensional complex systems through manifold learning and delayed embedding methods, and realizes the modeling and prediction of the complex system in low-dimensional space.
Published:
This paper explores the scaling laws of time series foundations and verifies the prediction performance of two mainstream Transformer architectures, Encoder-only and Decoder-only, on in-distribution and out-of-distribution data on a large-scale time series dataset. 
Published:
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.