Metraipolis › archive › dc_bdfbd959aa51

Temporal Predictive Multiplicity: Equally Accurate Time Series Models Yield Different Forecast Trajectories — arXiv:2610.09994

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09994
License (as archived)
CC0-1.0
Archived
2026-10-08T11:11:42.552Z
SHA-256 of the archived text
1b297452fc1f1f4f92e57565a881db91aaadb63b2b3ee2eef29f37654635cc93
Stable URL of this page
https://metraipolis.com/documento/dc_bdfbd959aa51

How to cite

Temporal Predictive Multiplicity: Equally Accurate Time Series Models Yield Different Forecast Trajectories — arXiv:2610.09994 — arXiv (en), https://arxiv.org/abs/2610.09994 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bdfbd959aa51 (Metraipolis archive dc_bdfbd959aa51, sha256 1b297452fc1f1f4f92e57565a881db91aaadb63b2b3ee2eef29f37654635cc93)
BibTeX
@misc{dcbdfbd959aa51,
  title = {Temporal Predictive Multiplicity: Equally Accurate Time Series Models Yield Different Forecast Trajectories — arXiv:2610.09994},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09994},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bdfbd959aa51; sha256 1b297452fc1f1f4f92e57565a881db91aaadb63b2b3ee2eef29f37654635cc93},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09994. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Models with near-identical predictive performance can yield substantially different predictions, a phenomenon known as predictive multiplicity. Prior work has mostly studied this at the level of individual scalar outputs. In time-series forecasting, however, predictions across horizons jointly define a trajectory, and horizon-wise comparisons can hide important differences in predictive behavior. To address this problem, we introduce temporal predictive multiplicity, a framework that characterizes disagreement over complete forecast trajectories among models with near-identical predictive performance. We show that constraining predictive performance alone can still admit a broad range of different trajectories. We further show that constraining multiplicity at individual horizons partially reduces, but does not eliminate, trajectory-level multiplicity. Experiments with 19 neural forecasting architectures on 11 datasets confirm that near-optimal models can exhibit substantial variability in the forecast trajectories they produce, and trajectory-level disagreement is largely unrelated to horizon-wise disagreement. Our framework, therefore, exposes a gap in existing multiplicity studies: models with indistinguishable predictive performance imply fundamentally different temporal trajectories, with consequential downstream effects.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.09994 — 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 2026-10-08T10:14:06.146Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).