Metraipolis › archive › dc_7b2128240fae
Evaluating Sequence Assembly Strategies for Differentially Private Synthetic Time-Series Forecasting — arXiv:2610.10222
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10222
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:36:11.067Z
- SHA-256 of the archived text
23994007e21b8a01d10d1dcf9e4b139c8548893ecfd7f025acfe6c0aee680082- Stable URL of this page
https://metraipolis.com/documento/dc_7b2128240fae
How to cite
Evaluating Sequence Assembly Strategies for Differentially Private Synthetic Time-Series Forecasting — arXiv:2610.10222 — arXiv (en), https://arxiv.org/abs/2610.10222 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b2128240fae (Metraipolis archive dc_7b2128240fae, sha256 23994007e21b8a01d10d1dcf9e4b139c8548893ecfd7f025acfe6c0aee680082)
BibTeX
@misc{dc7b2128240fae,
title = {Evaluating Sequence Assembly Strategies for Differentially Private Synthetic Time-Series Forecasting — arXiv:2610.10222},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10222},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b2128240fae; sha256 23994007e21b8a01d10d1dcf9e4b139c8548893ecfd7f025acfe6c0aee680082},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10222. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Differentially private time-series generators commonly produce fixed-length synthetic windows, whereas downstream forecasting models often require long continuous training sequences. How these windows are assembled after generation can therefore alter the effective synthetic data presented to a forecaster, even when the trained generator remains unchanged. We study this post-generation sequence assembly process by systematically varying overlap rates and window-weighting schemes and evaluating the resulting sequences in terms of boundary continuity, statistical and temporal fidelity, and Train-on-Synthetic-Test-on-Real (TSTR) forecasting utility. Across four types of public datasets (ETTh1, ETTm1, Weather, and Appliances) and five forecasting models, the results reveal a clear forecaster-dependent assembly principle: downstream TSTR utility is jointly shaped by the forecaster, overlap rate, and window-weighting scheme, leading to distinct assembly preferences across forecasting models. Increased overlap generally improves boundary continuity, but improvements in continuity or individual fidelity diagnostics do not consistently reduce forecasting error, indicating that these diagnostics alone are insufficient for selecting assembly configurations. Complete five-forecaster assembly grids, together with matched Train-on-Real-Test-on-Real (TRTR) references, further characterize these regularities and quantify assembly-dependent utility relative to real-data training. We then validate the identified principles through additional analyses of robustness and generator variability. 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/2610.10222 — 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 2026-10-08T12:14:15.316Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).