Skip to content
DraconiticResearch
Search Sources API
194,161 studies31 sourcesUpdated just now
PreprintCC BY 4.0arXiv

Bethe Hessian Recovery through the Kesten-Stigum Regime

Abstract

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× 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.

Related

  1. On Zeros and Algorithms for Disordered Systems II: The Antiferromagnetic Ising Model up to Kesten-Stigum
    Ferenc Bencs, Brice Huang, Daniel Z. Lee +2
    arXivPreprintarXiv licenceFull textMathematical physicsProbabilityarXiv
  2. The Value of Depth in Message Passing on Sparse Graphs: A Kesten-Stigum Dichotomy
    Aseem Raj Baranwal
    arXivPreprintCC BY 4.0Full textProbabilityStatisticsarXiv
  3. Slow Beats Fast at the Kesten-Stigum Threshold: Minimax, Fisher-Information and Belief-Propagation Characterizations of the Information-Computation Gap in Sparse Stochastic Block Models
    Soroor Ghandali
    arXivPreprintarXiv licenceFull textProbabilityStatisticsarXiv
  4. The oriented Kesten--McKay law for random regular digraphs
    Yukun He, Jiaoyang Huang
    arXivPreprintarXiv licenceFull textProbabilityarXiv
  5. Interior Hessian estimates for the quadratic Hessian equation
    Zhisu Li, Ke Wu
    arXivPreprintCC0Full text20 citedAnalysis & PDEsarXivOpenAlex
BibTeX
@misc{dong2026bethe,
  title = {{Bethe Hessian Recovery through the Kesten-Stigum Regime}},
  author = {Dingding Dong and Theo McKenzie},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.41802},
  eprint = {2610.41802},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.41802},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Bethe Hessian Recovery through the Kesten-Stigum Regime
AU  - Dingding Dong
AU  - Theo McKenzie
PY  - 2026
DA  - 2026/10/30
PB  - arXiv
DO  - 10.48550/arxiv.2610.41802
UR  - https://arxiv.org/abs/2610.41802
AB  - 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× 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.
ER  -