Pyproject.toml · README.md · Issues · Gitignore

Feb 4, 2024 · The concept of universal forecasting, emerging from pre-training on a vast collection of time series datasets, envisions a single Large Time ...

Trained on our newly introduced. Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine do- mains, MOIRAI achieves competitive ...

List of research papers focus on time series forecasting and deep learning, as well as other resources like competitions, datasets, courses, blogs, code, ...

This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF).

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting. ... Unified Training of Universal Time Series Forecasting Transformers. [Paper].

Jul 18, 2024 · Moirai, the Masked Encoder-based Universal Time Series Forecasting Transformer is a Large Time Series Model pre-trained on LOTSA data. For more ...

Venue, Title, Keywords. ICML'24, Unified Training of Universal Time Series Forecasting Transformers, Multivariate; Large-scale data; Variable window size.

[ICML2024] Unified Training of Universal Time Series Forecasting Transformers - uni2ts/pyproject.toml at main · SalesforceAIResearch/uni2ts.

Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game- ...