Metraipolis › archive › dc_eae21eeedf8f
StreamLTT: Risk Certification for Policy Selection under Stream Dependence — arXiv:2611.04062
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04062
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:40:44.667Z
- SHA-256 of the archived text
5ab243f2e180d26ed633a73958a4b1c630afff858bbf4e397f59cd4bf4dd8da8- Stable URL of this page
https://metraipolis.com/documento/dc_eae21eeedf8f
How to cite
StreamLTT: Risk Certification for Policy Selection under Stream Dependence — arXiv:2611.04062 — arXiv (en), https://arxiv.org/abs/2611.04062 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eae21eeedf8f (Metraipolis archive dc_eae21eeedf8f, sha256 5ab243f2e180d26ed633a73958a4b1c630afff858bbf4e397f59cd4bf4dd8da8)
BibTeX
@misc{dceae21eeedf8f,
title = {StreamLTT: Risk Certification for Policy Selection under Stream Dependence — arXiv:2611.04062},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04062},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eae21eeedf8f; sha256 5ab243f2e180d26ed633a73958a4b1c630afff858bbf4e397f59cd4bf4dd8da8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04062. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Learn-then-Test (LTT) provides a general framework for certifying deployment policies against a prescribed risk target, but its standard formulation targets a fixed population risk estimated from calibration losses. In sequential deployment, losses may instead be dependent and nonstationary, so the risk of a fixed policy can evolve with the observed history. We introduce StreamLTT, which replaces this fixed population risk with average predictable risk, defined by conditioning each decision's loss on the information available before its outcome is revealed. Conditional centering turns empirical deviations from this target into a martingale sum, enabling both a test that adapts to predictable variance and a finite-sample Hoeffding alternative. Combined with family-wise error rate control, StreamLTT yields a simultaneously certified policy region that supports subsequent deployment selection. Across seven forecasting datasets and seven deployment risks, StreamLTT places the certified frontier substantially closer to the prescribed risk target than IID, robust-variance, block-bootstrap, and concentration-based alternatives, while empirical family-wise error closely follows the prescribed level. A finite-sample ablation further shows that the predictable-risk formulation drives the tighter risk frontier, while adaptation to predictable variance makes more effective use of the available family-wise error budget. StreamLTT therefore extends risk-certified policy selection to dependent deployment streams by addressing both what risk should be certified and how it should be tested. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Statistics Theory (math.ST); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2611.04062 — 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 2026-11-04T12:29:47.269Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).