Metraipolis › archive › dc_c527481dbcfb

Self-Normalized Inference from Riemannian Stochastic Gradient Paths — arXiv:2611.01035

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01035
License (as archived)
CC0-1.0
Archived
2026-11-03T11:24:59.736Z
SHA-256 of the archived text
a1f1f18c728457d38b0dc8c7f0bc5286be0685e88d896c6ee3b8d0c45d856477
Stable URL of this page
https://metraipolis.com/documento/dc_c527481dbcfb

How to cite

Self-Normalized Inference from Riemannian Stochastic Gradient Paths — arXiv:2611.01035 — arXiv (en), https://arxiv.org/abs/2611.01035 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c527481dbcfb (Metraipolis archive dc_c527481dbcfb, sha256 a1f1f18c728457d38b0dc8c7f0bc5286be0685e88d896c6ee3b8d0c45d856477)
BibTeX
@misc{dcc527481dbcfb,
  title = {Self-Normalized Inference from Riemannian Stochastic Gradient Paths — arXiv:2611.01035},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01035},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c527481dbcfb; sha256 a1f1f18c728457d38b0dc8c7f0bc5286be0685e88d896c6ee3b8d0c45d856477},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01035. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Riemannian stochastic gradient paths estimate constrained parameters, but confidence regions usually require estimating the Hessian and gradient-noise covariance. We develop self-normalized inference from one path by expressing retained iterates in a common random tangent space. Their average and centered partial sums share an unknown covariance factor that cancels in a Brownian bridge pivot. Under suitable regularity conditions, a joint expansion of the averaged estimator and integrated path controls nonlinear coordinate errors using conditional second moments. The procedure uses fixed-dimensional memory and extends to nondegenerate smooth functionals and alternative local coordinates. Numerical studies show competitive coverage relative to plug-in Wald inference while avoiding Hessian and residual-density estimation.

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).
Pagina del lavoro: https://arxiv.org/abs/2611.01035 — 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 2026-11-03T11:02:37.800Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).