Metraipolis › archive › dc_795c3d6fee77

Bethe Hessian Recovery through the Kesten-Stigum Regime — arXiv:2610.41802

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41802
License (as archived)
CC0-1.0
Archived
2026-11-03T08:14:36.369Z
SHA-256 of the archived text
2f4ac0778cef6aeeb53138033ed11fbde373d30a99777b749bf28934c1ed65e1
Stable URL of this page
https://metraipolis.com/documento/dc_795c3d6fee77

How to cite

Bethe Hessian Recovery through the Kesten-Stigum Regime — arXiv:2610.41802 — arXiv (en), https://arxiv.org/abs/2610.41802 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_795c3d6fee77 (Metraipolis archive dc_795c3d6fee77, sha256 2f4ac0778cef6aeeb53138033ed11fbde373d30a99777b749bf28934c1ed65e1)
BibTeX
@misc{dc795c3d6fee77,
  title = {Bethe Hessian Recovery through the Kesten-Stigum Regime — arXiv:2610.41802},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41802},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_795c3d6fee77; sha256 2f4ac0778cef6aeeb53138033ed11fbde373d30a99777b749bf28934c1ed65e1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41802. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We show that outlier eigenvectors of the Bethe Hessian achieve weak recovery in the stochastic block model down to the Kesten-Stigum threshold, for every fixed common expected degree $d>1$. This extends previous recovery guarantees, which required $d$ to be sufficiently large. This threshold is information-theoretically optimal for the symmetric two-community model and is conjectured to mark the limit of efficient recovery in broader symmetric models. Our result matches the recovery guarantees of non-backtracking spectral methods while using Hermitian $n\times n$ matrices. To do this, we identify recursive formulas for the negative outlier eigenvalues and show that their eigenspaces have nonvanishing overlap with the corresponding planted eigenspaces. The proof constructs approximate eigenvectors from the planted labels on the limiting Poisson tree, with weights given by its Green's function, and transfers these approximations to the finite graph.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno).
Categorie arXiv: Statistics Theory (math.ST) ; Combinatorics (math.CO); Probability (math.PR); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.41802 — 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 2026-11-03T08:03:23.769Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).