Metraipolis › archive › dc_2c328caaed40

When Can We Trust the Matching Principle? Robust Deployment Geometry Under Finite-Sample and Model Uncertainty — arXiv:2610.02894

Source: arXiv
Original: https://arxiv.org/abs/2610.02894
License (as archived): CC0-1.0
Archived: 2026-10-05T22:50:20.955Z
SHA-256 of the archived text: 80ccc5d5d3babc752dd097420d51730fb58699b926b12803e3270ece51e5dfd4
Stable URL of this page: https://metraipolis.com/documento/dc_2c328caaed40

How to cite

When Can We Trust the Matching Principle? Robust Deployment Geometry Under Finite-Sample and Model Uncertainty — arXiv:2610.02894 — arXiv, https://arxiv.org/abs/2610.02894 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2c328caaed40 (Metraipolis archive dc_2c328caaed40, sha256 80ccc5d5d3babc752dd097420d51730fb58699b926b12803e3270ece51e5dfd4)

BibTeX

@misc{dc2c328caaed40,
  title = {When Can We Trust the Matching Principle? Robust Deployment Geometry Under Finite-Sample and Model Uncertainty — arXiv:2610.02894},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02894},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2c328caaed40; sha256 80ccc5d5d3babc752dd097420d51730fb58699b926b12803e3270ece51e5dfd4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02894. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Match only geometry you can identify; otherwise spread the penalty. We quantify that decision by the trust ratio tau = epsilon / gamma (estimation uncertainty over spectral separation). Under the linear-quadratic Matching response, oracle-relative drift between estimated and oracle projector matching scales as tau^2 for probes in the chosen top-r deployment subspace -- O(tau^2) in the Davis-Kahan separation region tau < 1/2, with practical usefulness depending on constants. Confidence-Calibrated Matching (CCM) turns tau into a policy -- directional when tau is small, progressively isotropic when not -- with thresholds from calibration, not from the theorem (match sits in the separation region; soft is mostly heuristic). Experiments show both regimes, including UCI HAR embeddings where always-match is worse than abstain on every cell.

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/2610.02894 — 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 2026-10-05T22:45:55.809Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).