Metraipolis › archive › dc_07cdc50dfad2

QUAL: Quantile Alignment Improves Zero-Shot Time-Series Foundation Models — arXiv:2610.41100

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41100
License (as archived): CC0-1.0
Archived: 2026-11-03T07:31:19.733Z
SHA-256 of the archived text: 53e59178a2bfee46ad09c25e28fef4432f64beb51b69a543e33ac5c7c2a5e9d4
Stable URL of this page: https://metraipolis.com/documento/dc_07cdc50dfad2

How to cite

QUAL: Quantile Alignment Improves Zero-Shot Time-Series Foundation Models — arXiv:2610.41100 — arXiv (en), https://arxiv.org/abs/2610.41100 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07cdc50dfad2 (Metraipolis archive dc_07cdc50dfad2, sha256 53e59178a2bfee46ad09c25e28fef4432f64beb51b69a543e33ac5c7c2a5e9d4)

BibTeX

@misc{dc07cdc50dfad2,
  title = {QUAL: Quantile Alignment Improves Zero-Shot Time-Series Foundation Models — arXiv:2610.41100},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41100},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07cdc50dfad2; sha256 53e59178a2bfee46ad09c25e28fef4432f64beb51b69a543e33ac5c7c2a5e9d4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41100. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Time-series foundation models (TSFMs) provide zero-shot forecasts for unseen series, but their accuracy varies across datasets. Combining several models can reduce this variability, yet zero-shot deployment provides no target labels for selecting or weighting them. We find that a model pool is useful not only as a final ensemble, but also as a probability reference for transforming each member forecast. Aligning quantiles through this pool-relative reference improves every member forecast in aggregate. Motivated by this finding, we propose QUAL (Quantile alignment), a simple label-free framework for improving and combining diverse TSFMs. QUAL first produces aligned member forecasts, then applies Huber aggregation and rearrangement to obtain a robust combined forecast without training or model modification. On GIFT-Eval, quantile alignment reduces average member MASE and CRPS by 7.4% and 9.8%. The full framework remains robust when weak forecasters enter a candidate pool whose quality cannot be verified in advance. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41100 — 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 2026-11-03T07:29:33.596Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).