Metraipolis › archive › dc_7fa0d7beef2f

Instance-Specific Sharp Convergence Rate of the Add-$λ$ Estimator via Feature Space Decomposition — arXiv:2611.01828

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01828
License (as archived): CC0-1.0
Archived: 2026-11-03T18:46:37.104Z
SHA-256 of the archived text: 9f8fd9e5027ef64978475009ef3bf25abb2cfedb4ac99396aee814148de1a4f7
Stable URL of this page: https://metraipolis.com/documento/dc_7fa0d7beef2f

How to cite

Instance-Specific Sharp Convergence Rate of the Add-$λ$ Estimator via Feature Space Decomposition — arXiv:2611.01828 — arXiv (en), https://arxiv.org/abs/2611.01828 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7fa0d7beef2f (Metraipolis archive dc_7fa0d7beef2f, sha256 9f8fd9e5027ef64978475009ef3bf25abb2cfedb4ac99396aee814148de1a4f7)

BibTeX

@misc{dc7fa0d7beef2f,
  title = {Instance-Specific Sharp Convergence Rate of the Add-$λ$ Estimator via Feature Space Decomposition — arXiv:2611.01828},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01828},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7fa0d7beef2f; sha256 9f8fd9e5027ef64978475009ef3bf25abb2cfedb4ac99396aee814148de1a4f7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01828. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Using the Feature Space Decomposition framework, we establish non-asymptotic matching upper and lower bounds for the expected Kullback-Leibler estimation error of the Add-$\lambda$ estimator of a discrete probability distribution, for any signal, any dimension, any sample size, and any $\lambda>0$.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.ST, nuovi lavori del giorno).
Categorie arXiv: Information Theory (cs.IT) ; Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2611.01828 — 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 2026-11-03T18:14:52.877Z dalla pagina https://arxiv.org/list/math.ST/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).