Metraipolis › archive › dc_efbdf299f845

Zero-SNR Analyticity of the Scalar MMSE Is Equivalent to Gaussianity — arXiv:2609.15048

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.15048
License (as archived)
CC0-1.0
Archived
2026-10-16T00:15:43.243Z
SHA-256 of the archived text
caa024b4e71ba32cf625e740eec103132b56c9cfb2eb9a2502d4ea985f36c4bd
Stable URL of this page
https://metraipolis.com/documento/dc_efbdf299f845

How to cite

Zero-SNR Analyticity of the Scalar MMSE Is Equivalent to Gaussianity — arXiv:2609.15048 — arXiv (en), https://arxiv.org/abs/2609.15048 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_efbdf299f845 (Metraipolis archive dc_efbdf299f845, sha256 caa024b4e71ba32cf625e740eec103132b56c9cfb2eb9a2502d4ea985f36c4bd)
BibTeX
@misc{dcefbdf299f845,
  title = {Zero-SNR Analyticity of the Scalar MMSE Is Equivalent to Gaussianity — arXiv:2609.15048},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15048},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_efbdf299f845; sha256 caa024b4e71ba32cf625e740eec103132b56c9cfb2eb9a2502d4ea985f36c4bd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15048. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Let $Y_s=\sqrt{s}X+Z$, where $Z$ is standard Gaussian and independent of the real random variable $X$. We prove that, under the square-exponential moment condition $\mathbb{E}e^{\beta X^2}<\infty$ for some $\beta>0$, the scalar minimum mean-square error $\operatorname{mmse}_X(s)$ is analytic at zero signal-to-noise ratio if and only if $X$ is Gaussian, with constant random variables included as degenerate Gaussians. The proof converts estimation in the Gaussian channel into a backward heat flow acting on the moment-generating function $M(z)=\mathbb{E}e^{zX}$. Under the stated tail condition, every non-Gaussian input forces $M$ to have a nonzero complex zero. We show that each zero cluster produces a finite singularity in its localized Borel transform at the action $\xi=z_0^2/2$. After removing the action scale, the Borel coefficients have a nonzero $n^{-1/2}$ prefactor for a simple zero. A zero of multiplicity $m\geq 2$ splits according to the roots of a Hermite polynomial and instead contributes a prefactor $n^{-m/2}e^{r_m\sqrt{2n}}$. A finite-disc localization and relative-cycle continuation argument then show that at least one such singularity survives in the full Borel transform. Thus, for every non-Gaussian input in the stated class, the formal zero-SNR expansion is Gevrey-1 but divergent. Rational-MMSE rigidity and the analogous analyticity criterion for mutual information follow as corollaries.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Information Theory (cs.IT) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.15048 — 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 2026-10-15T23:54:14.941Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).