Metraipolis › archive › dc_5508bb91a499
A Unified Scaling Law for Time Series Foundation Models — arXiv:2610.05269
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05269
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:30:59.026Z
- SHA-256 of the archived text
cf9a2d58f29e65a9d9c4333dfe00c363b888a72b4ca45a85b8037511f4a6ad0b- Stable URL of this page
https://metraipolis.com/documento/dc_5508bb91a499
How to cite
A Unified Scaling Law for Time Series Foundation Models — arXiv:2610.05269 — arXiv, https://arxiv.org/abs/2610.05269 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5508bb91a499 (Metraipolis archive dc_5508bb91a499, sha256 cf9a2d58f29e65a9d9c4333dfe00c363b888a72b4ca45a85b8037511f4a6ad0b)
BibTeX
@misc{dc5508bb91a499,
title = {A Unified Scaling Law for Time Series Foundation Models — arXiv:2610.05269},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05269},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5508bb91a499; sha256 cf9a2d58f29e65a9d9c4333dfe00c363b888a72b4ca45a85b8037511f4a6ad0b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05269. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We develop a Unified Scaling Law and a Unified Theory of Time Series Learning to understand how model capacity and historical information support forecasting. Across different lookback lengths and forecast horizons, we analyze 18,768 experimental cells from 21 checkpoints on 23 dataset-frequency tasks spanning six domains. Our empirical methodology integrates local resource relations into a parsimonious, fitted five-parameter law: capacity gains increase with history, context gains diminish toward saturation, and horizon effects enter as a common shift. Fitted without Toto 2.0, the law predicts its horizon-averaged capacity-scaling curves with mean absolute percentage errors of 1.09% and 1.50% at input lengths 2048 and 4096. To understand how history supports prediction, our learning theory uses Gaussian regression to analyze rule identification and predictive capability. We hypothesize that full-shot models learn by accumulating information in weights, while frozen time series foundation models (TSFMs) use history by extracting information through activations. Matched-history comparisons establish the predictive value of additional history. Controlled parameter exchanges and activation interventions provide evidence that history-derived rule information can be retained, reused across queries, and used to recover a contribution to long-context prediction. Together, these findings inform capacity scaling, context allocation, and the development of models that retain and apply historical rules. Code and main results are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.05269 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:27:05.777Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).