Metraipolis › archive › dc_54732ca6fecc

Exact Global Minimax Risk near Nonidentification — arXiv:2610.32546

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.32546
License (as archived)
CC0-1.0
Archived
2026-10-26T20:14:37.275Z
SHA-256 of the archived text
46f5bd4bd194978d0b0ba32e1edc0d6e98f9866a5533db07fc1712e7e9897eec
Stable URL of this page
https://metraipolis.com/documento/dc_54732ca6fecc

How to cite

Exact Global Minimax Risk near Nonidentification — arXiv:2610.32546 — arXiv (en), https://arxiv.org/abs/2610.32546 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_54732ca6fecc (Metraipolis archive dc_54732ca6fecc, sha256 46f5bd4bd194978d0b0ba32e1edc0d6e98f9866a5533db07fc1712e7e9897eec)
BibTeX
@misc{dc54732ca6fecc,
  title = {Exact Global Minimax Risk near Nonidentification — arXiv:2610.32546},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.32546},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_54732ca6fecc; sha256 46f5bd4bd194978d0b0ba32e1edc0d6e98f9866a5533db07fc1712e7e9897eec},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32546. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study squared-error estimation when a nuisance parameter is unidentified on a submodel but affects a target that vanishes there. For models with higher-order profile expansions, we give sufficient conditions under which the largest critical-path minimax risk is the exact asymptotic minimax risk over the full parameter space. An efficient observable feature, negligible calibration error and stable recovery yield one estimator attaining the leading constant uniformly, with the profile coordinates unknown. The estimator uses calibration estimates, a local feature mean and an empirical recovery feature. The constant is expressed through a bounded-normal decision problem. We verify the conditions in two models. In centered Gaussian logistic errors-in-variables regression with one surrogate and two unknown variances, we determine the fifth-order global coefficient risk and its exact constant. A sparse extension separates variance-decomposition uncertainty from direction estimation and specifies when the scalar constant is preserved. In a degree-balanced replicated-network model, we determine the sixth-order global edge-contrast risk when block proportions are unknown. Triangles identify a parameter combination; a bowtie supplies the additional information needed for the contrast.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2610.32546 — 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 2026-10-26T19:49:03.492Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).