Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives
We introduce Timer-M1, a pretrained multivariate time series foundation model that learns with primitives for zero-shot forecasting.
Key points
- Across domains, time series share elementary temporal and relational patterns, termed primitives, yet differ in how these primitives manifest and evolve across different contexts.
- To this end, we develop a primitive-based data synthesis and pretraining pipeline.
- The synthesis pipeline generates series with temporal primitives shared across domains and then assembles real and generated series into multivariate samples using relational primitives.
- These results support effective primitive-based pretraining as a route to robust general forecasting technique across domains and task settings.
Sources (1)
- [1]Timer-M1: A Multivariate Time Series Foundation Model via Learning PrimitivesarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 11:28 AM
We introduce Timer-M1, a pretrained multivariate time series foundation model that learns with primitives for zero-shot forecasting.
Across domains, time series share elementary temporal and relational patterns, termed primitives, yet differ in how these primitives manifest and evolve across different contexts.
Extractive summary: sentences quoted from the sources.