Metraipolis › archive › dc_41f9526cdf56

Conditional Fisher-Information Central Limit Theorems under Log-Concavity with Information-Theoretic Consequences — arXiv:2609.07150

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07150
License (as archived)
CC0-1.0
Archived
2026-10-16T14:35:31.866Z
SHA-256 of the archived text
c04f634b33db6f8453cae2e41f59943587b0f900c3843b39f400070629a44c93
Stable URL of this page
https://metraipolis.com/documento/dc_41f9526cdf56

How to cite

Conditional Fisher-Information Central Limit Theorems under Log-Concavity with Information-Theoretic Consequences — arXiv:2609.07150 — arXiv (en), https://arxiv.org/abs/2609.07150 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_41f9526cdf56 (Metraipolis archive dc_41f9526cdf56, sha256 c04f634b33db6f8453cae2e41f59943587b0f900c3843b39f400070629a44c93)
BibTeX
@misc{dc41f9526cdf56,
  title = {Conditional Fisher-Information Central Limit Theorems under Log-Concavity with Information-Theoretic Consequences — arXiv:2609.07150},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07150},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_41f9526cdf56; sha256 c04f634b33db6f8453cae2e41f59943587b0f900c3843b39f400070629a44c93},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07150. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We establish conditional central limit theorems in Fisher information under log-concavity in every fixed dimension. For conditionally centered normalized sums, after whitening by the averaged conditional covariance, the averaged conditional Fisher information converges to the dimension if and only if it is finite at one convolution level. The scalar criterion follows as the one-dimensional case; we also provide an independent scalar proof based on a second-order continuity theorem for Fisher production on Gaussian-smoothed, tail-controlled classes. For the original sums, the averaged Fisher information matrix converges in operator norm to the inverse averaged conditional covariance. Consequently, the conditional relative Fisher information with respect to the limiting Gaussian law vanishes, and the Gaussian logarithmic Sobolev inequality yields convergence in conditional relative entropy and conditional entropy. We give two operational consequences. For any fixed finite-constellation low-power input, the first-order conditional mutual-information slope converges to the Gaussian-noise benchmark. For Gaussian signaling at any fixed signal covariance, the mutual-information gap from that benchmark is bounded by the conditional relative Fisher deficit and hence vanishes asymptotically.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-09 in math.PR).
Categorie arXiv: Information Theory (cs.IT) ; Probability (math.PR).
Pagina del lavoro: https://arxiv.org/abs/2609.07150 — 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 2026-10-16T14:09:59.843Z dalla pagina https://arxiv.org/catchup/math.PR/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).