Metraipolis › archive › dc_bb2fa9e6f0ab
Optimal Inference with Black-box Predictions — arXiv:2608.10155
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10155
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:22:39.947Z
- SHA-256 of the archived text
bb72329eb974b30b777535ced7e5121bb8e7b8758fbc0d19d3272e082bcdaa1f- Stable URL of this page
https://metraipolis.com/documento/dc_bb2fa9e6f0ab
How to cite
Optimal Inference with Black-box Predictions — arXiv:2608.10155 — arXiv (en), https://arxiv.org/abs/2608.10155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb2fa9e6f0ab (Metraipolis archive dc_bb2fa9e6f0ab, sha256 bb72329eb974b30b777535ced7e5121bb8e7b8758fbc0d19d3272e082bcdaa1f)
BibTeX
@misc{dcbb2fa9e6f0ab,
title = {Optimal Inference with Black-box Predictions — arXiv:2608.10155},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10155},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb2fa9e6f0ab; sha256 bb72329eb974b30b777535ced7e5121bb8e7b8758fbc0d19d3272e082bcdaa1f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Powerful black-box predictive models have motivated many proposals for combining observed data with predictions to perform valid statistical inference. Despite this progress, the field lacks a unifying principle that explains how hypothesis tests should integrate data and predictions in a way that is both valid and efficient. In this work, we address this gap in the high-dimensional Gaussian sequence model. We characterize the information-theoretic limits of inference with black-box predictions when their accuracies are known and, for orthogonal predictions, when they are unknown. Building on these characterizations, we develop practical hypothesis tests that adapt to the unknown accuracies of the predictions while benefiting from strong alignment among them. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in stat.ML). Categorie arXiv: Statistics Theory (math.ST) ; Methodology (stat.ME); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2608.10155 — 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 2026-10-19T06:15:21.787Z dalla pagina https://arxiv.org/catchup/stat.ML/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).