arXiv · 2611.16934
Time Flies When You Parallelise: Pareto-efficient Time Series Foundation Models with Linear Recurrences
Abstract
Time series foundation models have demonstrated strong zero-shot forecasting performance, but computational efficiency remains a central architectural challenge. Temporal self-attention incurs quadratic cost in the number of temporal tokens, while nonlinear recurrent state transitions restrict parallel computation along the temporal dimension. We introduce ci-proto, a family of time series foundation models based on Mamba-3, whose linear state recurrences support chunk-wise parallel-in-time computation during training, and inference costs that scale linearly with sequence length. The architecture alternates recurrent temporal processing with cross-variate attention, supporting multivariate probabilistic forecasting with past-only and future-known covariates. Across fev-bench's 100 forecasting tasks, ci-proto XL sets a new state of the art among time series foundation models. The five ci-proto variants also make up the entire Pareto frontier for mean scaled quantile loss and mean absolute scaled error against both parameter count and median runtime.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Torben Berndt, Lingyi Yang, Federico Nardi, Yi Heng Lim, AJ Shears, Benjamin Walker. 2026-11-13. Time Flies When You Parallelise: Pareto-efficient Time Series Foundation Models with Linear Recurrences. https://searcharxiv.com/abs/2611.16934
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.