Metraipolis › archive › dc_db04224a95ea
RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting — arXiv:2610.00405
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00405
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T15:33:18.997Z
- SHA-256 of the archived text
bb2a1a971305796fb06ce333fe1bfbdf9d60a833b3bdcdf52f2e7b506f1483ea- Stable URL of this page
https://metraipolis.com/documento/dc_db04224a95ea
How to cite
RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting — arXiv:2610.00405 — arXiv (en), https://arxiv.org/abs/2610.00405 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db04224a95ea (Metraipolis archive dc_db04224a95ea, sha256 bb2a1a971305796fb06ce333fe1bfbdf9d60a833b3bdcdf52f2e7b506f1483ea)
BibTeX
@misc{dcdb04224a95ea,
title = {RACE: Residual-Aware Test-Time Adaptation for Neighbor-Rich Time-Series Foundation Model Forecasting — arXiv:2610.00405},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00405},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db04224a95ea; sha256 bb2a1a971305796fb06ce333fe1bfbdf9d60a833b3bdcdf52f2e7b506f1483ea},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00405. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Time-series foundation models (TSFMs) perform strongly across forecasting tasks, but their per-series inference is ill-suited to neighbor-rich forecasting, where each query has access to related but nonidentical historical series. Continuous glucose monitoring (CGM) and Web/cloud workloads exemplify this setting: CGM trajectories share physiological patterns but vary across individuals, devices, and conditions, while Web/cloud workloads combine common operating regimes with non-stationarity, heavy tails, and bursts. These histories share useful structure, yet neighbors are not equally relevant. Existing methods either fine-tune TSFMs for each target domain, incurring additional costs and offering limited transferability across backbones, or append retrieved series without verifying whether they support the current forecast. The key challenges are conflicting residual evidence from neighboring series and residual patterns that vary across TSFMs and forecasting tasks. We formulate test-time neighborhood scaling: using same-domain neighbor evidence without modifying the backbone. We propose RACE (Residual-Aware Correction of Forecasting Errors), a two-stage framework for using historical neighbors. We first retrieve query-compatible neighbors, align their residuals to the query scale, and aggregate coherent evidence into the training-free RACE-TF correction. Full RACE then uses a lightweight, domain-specific Gate to determine when applying the correction is beneficial, with a reusable training workflow across TSFM backbones. Across four TSFMs, RACE improves all three domain-aggregate metrics on both primary domains, with the largest gains on high-error queries. Within each domain, a Gate trained on one TSFM transfers to other backbones without adaptation, and the resulting pipeline improves all 72 cross-backbone metric comparisons over the matched frozen targets. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-02 in stat.ML). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2610.00405 — 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 2026-10-06T15:12:55.884Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).