Metraipolis › archive › dc_c4376bc66fb4
Seq-Flow: Efficient Probabilistic Forecasting with Self-Rollout Error Control — arXiv:2610.10440
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10440
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:36:29.767Z
- SHA-256 of the archived text
de559db59420f559f6471a6bfa38b654f6bc447b9737357afe5b7b2e77e42146- Stable URL of this page
https://metraipolis.com/documento/dc_c4376bc66fb4
How to cite
Seq-Flow: Efficient Probabilistic Forecasting with Self-Rollout Error Control — arXiv:2610.10440 — arXiv (en), https://arxiv.org/abs/2610.10440 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c4376bc66fb4 (Metraipolis archive dc_c4376bc66fb4, sha256 de559db59420f559f6471a6bfa38b654f6bc447b9737357afe5b7b2e77e42146)
BibTeX
@misc{dcc4376bc66fb4,
title = {Seq-Flow: Efficient Probabilistic Forecasting with Self-Rollout Error Control — arXiv:2610.10440},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10440},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c4376bc66fb4; sha256 de559db59420f559f6471a6bfa38b654f6bc447b9737357afe5b7b2e77e42146},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10440. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many scientific forecasting tasks require updating a distribution over future trajectories as new observations arrive. Conventional diffusion and flow models generate each forecast from Gaussian noise, often at the cost of many sampling steps. Warm-start methods reuse earlier predictions to reduce this cost, but their models are not trained to perform the forecast update itself, which can compromise quality under few-step sampling. In this work, we introduce Seq-Flow, a conditional flow model whose ODE transports samples from the previous forecast distribution to the updated one. Because successive forecasts often differ only modestly, this transport starts from an informative distribution and can produce accurate updates with few flow evaluations. Recursive reuse also creates a challenge: errors in one forecast become errors in the initial states of subsequent flows. We address this with self-rollout training, in which a moving average copy of the model generates forecasts that initialize later training updates. Unlike self-forcing methods, which reuse generated outputs as conditioning context, Seq-Flow reuses them as the source of the next flow. Experiments On particle-accelerator beam spill forecasting show Seq-Flow reduces CRPS by 65% under a few-NFE sampling budget, while remaining competitive with strong baselines on fluid-dynamics forecasting tasks. Although trained on self-rollouts of at most four updates, Seq-Flow remains accurate over more than 400 consecutive updates. Our code is 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/2610.10440 — 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 2026-10-08T12:14:15.349Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).