pith. sign in

arxiv: 2605.19894 · v1 · pith:IV3UXI34new · submitted 2026-05-19 · 🧮 math.PR · math.ST· stat.TH

Sharp Spectral Thresholds for Multi-View Spiked Wigner Models

Xiaodong Yang , Subhabrata Sen , Yue M. Lu This is my paper

Pith reviewed 2026-05-20 01:46 UTC · model grok-4.3

classification 🧮 math.PR math.STstat.TH
keywords multi-view spiked Wigner modelspectral thresholdlinearized AMPweak recoveryphase transitioninformation-theoretic thresholdmatrix Dyson equationspike priors
0
0 comments X

The pith

In multi-view spiked Wigner models, SNR(λ, B) = 1 marks the exact spectral threshold for weak recovery with linearized AMP.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper studies a model with multiple noisy matrix observations sharing correlated latent spikes. It builds a spectral estimator from linearized approximate message passing and derives an explicit formula for the critical transition point. The quantity SNR(λ, B) equals the largest eigenvalue of Diag(√λ) times (B elementwise multiplied by B) times Diag(√λ). Below this value the spectrum stays inside the bulk with no informative outlier; above it an outlier appears at eigenvalue 1 whose eigenvector overlaps with the true signals. For a broad family of spike distributions this same point coincides with the information-theoretic limit for detecting the signals, so an efficient algorithm reaches the statistical optimum.

Core claim

For L ≥ 2 views, letting λ be the vector of spike strengths and B the limiting Gram matrix of the spikes, the critical parameter is SNR(λ, B) = λ_max[Diag(√λ) (B ⊙ B) Diag(√λ)]. When SNR(λ, B) < 1 the linearized AMP matrix has no outlier beyond the right edge of its bulk spectrum. When SNR(λ, B) > 1 an informative outlier is pinned at 1 and the associated eigenvector has explicit nontrivial overlaps with the latent signals. Thus SNR(λ, B) = 1 is the exact spectral weak-recovery threshold for linearized AMP. For a broad class of spike priors this threshold coincides with the information-theoretic threshold for weak recovery.

What carries the argument

The SNR(λ, B) = λ_max[Diag(√λ) (B ⊙ B) Diag(√λ)], which determines whether the linearized AMP matrix develops an outlier eigenvalue at 1 by combining the matrix Dyson equation description of the correlated noise with finite-rank perturbation arguments for the multi-view spikes.

If this is right

  • When SNR(λ, B) > 1 the eigenvector of the outlier provides a nontrivial estimator for the latent signals.
  • The threshold SNR(λ, B) = 1 is sharp for the linearized AMP spectral method.
  • For broad spike priors there is no statistical-computational gap because the spectral method achieves the information-theoretic limit.
  • The same transition governs performance in multimodal estimation tasks that produce several correlated noisy matrices.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same SNR formula could be tested as an approximate guide for recovery thresholds in non-Gaussian or non-linear multi-view observation models.
  • Designers of sensor arrays or imaging systems could choose the number of views or signal strengths so that the resulting SNR(λ, B) exceeds 1.
  • The absence of a gap suggests that similar linearization techniques may close computational gaps in other matrix estimation problems with structured correlations.

Load-bearing premise

The matrix Dyson equation together with finite-rank perturbation arguments correctly locates the outlier eigenvalue and its existence for the correlated Gaussian noise matrix in the multi-view spike structure.

What would settle it

Generate a numerical realization of the linearized AMP matrix with chosen λ and B such that SNR(λ, B) equals 0.99 versus 1.01; check whether an eigenvalue appears at 1 with eigenvector overlap to the planted spike only in the second case.

Figures

Figures reproduced from arXiv: 2605.19894 by Subhabrata Sen, Xiaodong Yang, Yue M. Lu.

Figure 1
Figure 1. Figure 1: Comparing empirical spectral distribution with theoretical predictions. Throughout, [PITH_FULL_IMAGE:figures/full_fig_p013_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Comparing empirical top eigenvalues and overlaps with theoretical predictions. Through [PITH_FULL_IMAGE:figures/full_fig_p014_2.png] view at source ↗
read the original abstract

Motivated by multimodal estimation, we study a multi-view spiked Wigner model in which several noisy matrix observations contain correlated latent spikes. We derive a spectral estimator for the latent spikes by linearizing approximate message passing (AMP). Our main result is an explicit sharp transition formula for its spectrum: for $L \geq 2$ views, letting $\lambda$ be the $L$-dimensional vector of spike strengths and $B$ the $L\times L$ limiting Gram matrix of the spikes, the critical parameter is $\mathsf{SNR}(\lambda,B)=\lambda_{\max}[\mathrm{Diag}(\sqrt{\lambda}) (B \odot B) \mathrm{Diag}(\sqrt{\lambda})]$. When $\mathsf{SNR}(\lambda,B)<1$, the linearized AMP matrix has no outlier beyond the right edge of its bulk spectrum. When $\mathsf{SNR}(\lambda,B)>1$, an informative outlier is pinned at the distinguished point $1$, and the associated eigenvector has explicit, nontrivial overlaps with the latent signals. Thus $\mathsf{SNR}(\lambda,B)=1$ gives the exact spectral weak-recovery threshold for the linearized AMP method. To establish our results, we analyze the correlated Gaussian noise matrix through a matrix Dyson equation and combine this deterministic description with finite-rank perturbation arguments adapted to the multi-view spike structure. We also show that, for a broad class of spike priors, the spectral threshold $\mathsf{SNR}(\lambda,B)=1$ coincides with the information-theoretic threshold for weak recovery, ruling out a statistical-computational gap for this class of priors.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 0 minor

Summary. The manuscript studies a multi-view spiked Wigner model motivated by multimodal estimation, in which L≥2 noisy matrix observations contain correlated latent spikes. A spectral estimator is derived by linearizing approximate message passing (AMP). The main result is an explicit sharp transition formula: with λ the L-dimensional vector of spike strengths and B the L×L limiting Gram matrix of the spikes, the critical parameter is SNR(λ,B)=λ_max[Diag(√λ)(B⊙B)Diag(√λ)]. When SNR(λ,B)<1 the linearized AMP matrix has no outlier beyond the right edge of the bulk spectrum; when SNR(λ,B)>1 an informative outlier is pinned at 1 whose eigenvector has explicit nontrivial overlaps with the latent signals. Thus SNR(λ,B)=1 is claimed to be the exact spectral weak-recovery threshold. The proof analyzes the correlated Gaussian noise via a matrix Dyson equation combined with finite-rank perturbation arguments adapted to the multi-view structure. For a broad class of spike priors the spectral threshold is shown to coincide with the information-theoretic threshold for weak recovery, ruling out a statistical-computational gap.

Significance. If the derivation holds, the work supplies a precise, explicit characterization of the spectral phase transition in a multi-view spiked model, extending single-view results to correlated observations. The explicit SNR formula obtained from the matrix Dyson equation and adapted finite-rank perturbations constitutes a technical advance for analyzing outlier eigenvalues in correlated random matrices. The additional claim that the algorithmic threshold matches the information-theoretic threshold for broad priors is significant, as it identifies a regime without statistical-computational gap in multimodal estimation.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the detailed summary of our work and for recognizing the significance of the explicit SNR formula derived via the matrix Dyson equation together with the absence of a statistical-computational gap for broad spike priors. We note the 'uncertain' recommendation and hope the full proofs in the manuscript address any concerns about the technical arguments. Since the report lists no specific major comments under the MAJOR COMMENTS section, we provide no point-by-point responses below.

Circularity Check

0 steps flagged

No significant circularity in derivation

full rationale

The abstract presents the SNR(λ,B) threshold as an explicit formula derived via matrix Dyson equation analysis of the correlated noise combined with finite-rank perturbation arguments adapted to the multi-view structure. This is not defined in terms of itself, nor is any prediction fitted to a subset and then re-labeled as output. No load-bearing self-citations or uniqueness theorems from prior author work are invoked in the provided text. The derivation chain is therefore self-contained against external random-matrix benchmarks and does not reduce to its inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

Abstract-only review limits visibility into exact assumptions; the work relies on standard random-matrix properties of correlated Gaussians and finite-rank perturbations, with no free parameters or invented entities explicitly introduced in the abstract.

axioms (2)
  • domain assumption The noise matrices are correlated Gaussians whose limiting behavior is captured by a matrix Dyson equation.
    Invoked to obtain the deterministic description of the bulk spectrum.
  • domain assumption Finite-rank perturbation arguments can be adapted to the multi-view spike structure.
    Used to locate the outlier eigenvalue and its eigenvector overlaps.

pith-pipeline@v0.9.0 · 5793 in / 1289 out tokens · 51392 ms · 2026-05-20T01:46:21.642264+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

192 extracted references · 192 canonical work pages · 6 internal anchors

  1. [1]

    Stability of the matrix dyson equation and random matrices with correlations

    Oskari H Ajanki, L \'a szl \'o Erd o s, and Torben Kr \"u ger. Stability of the matrix dyson equation and random matrices with correlations. Probability Theory and Related Fields , 173:293--373, 2019

    work page 2019

  2. [2]

    The dyson equation with linear self-energy: spectral bands, edges and cusps

    Johannes Alt, L \'a szl \'o Erd o s, and Torben Kr \"u ger. The dyson equation with linear self-energy: spectral bands, edges and cusps. Documenta Mathematica , 25:1421--1539, 2020

    work page 2020

  3. [3]

    o s, Torben H Kr \

    Johannes Alt, L \'a szl \'o Erd \"o s, Torben H Kr \"u ger, and Yuriy Nemish. Location of the spectrum of kronecker random matrices. In Annales de l'institut Henri Poincare , volume 55, 2019

    work page 2019

  4. [4]

    o s, Torben H Kr \

    Johannes Alt, L \'a szl \'o Erd \"o s, Torben H Kr \"u ger, and Dominik J Schr \"o der. Correlated random matrices: Band rigidity and edge universality. Annals of Probability , 48(2), 2020

    work page 2020

  5. [5]

    An introduction to random matrices

    Greg W Anderson, Alice Guionnet, and Ofer Zeitouni. An introduction to random matrices . Number 118. Cambridge university press, 2010

    work page 2010

  6. [6]

    Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices

    Jinho Baik, G \'e rard Ben Arous, and Sandrine P \'e ch \'e . Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices. Annals of Probability , pages 1643--1697, 2005

    work page 2005

  7. [8]

    The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices

    Florent Benaych-Georges and Raj Rao Nadakuditi. The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices. Advances in Mathematics , 227(1):494--521, 2011

    work page 2011

  8. [9]

    An iterative construction of solutions of the tap equations for the sherrington--kirkpatrick model

    Erwin Bolthausen. An iterative construction of solutions of the tap equations for the sherrington--kirkpatrick model. Communications in Mathematical Physics , 325(1):333--366, 2014

    work page 2014

  9. [10]

    Global and individualized community detection in inhomogeneous multilayer networks

    Shuxiao Chen, Sifan Liu, and Zongming Ma. Global and individualized community detection in inhomogeneous multilayer networks. The Annals of Statistics , 50(5):2664--2693, 2022

    work page 2022

  10. [11]

    Asymptotic mutual information for the balanced binary stochastic block model

    Yash Deshpande, Emmanuel Abbe, and Andrea Montanari. Asymptotic mutual information for the balanced binary stochastic block model. Information and Inference: A Journal of the IMA , 6(2):125--170, 2017

    work page 2017

  11. [12]

    Optimal spectral algorithms for correlated two-view models in high dimensions

    Hang Du, Henry Hu, and Saba Lepsveridze. Optimal spectral algorithms for correlated two-view models in high dimensions. personal communication , 2026

    work page 2026

  12. [13]

    Averaging fluctuations in resolvents of random band matrices

    L \'a szl \'o Erd o s, Antti Knowles, and Horng-Tzer Yau. Averaging fluctuations in resolvents of random band matrices. In Annales Henri Poincar \'e , volume 14, pages 1837--1926. Springer, 2013

    work page 1926

  13. [14]

    The local semicircle law for a general class of random matrices

    L \'a szl \'o Erdos, Antti Knowles, Horng-Tzer Yau, and Jun Yin. The local semicircle law for a general class of random matrices. Electron. J. Probab , 18(59):1--58, 2013

    work page 2013

  14. [16]

    A dynamical approach to random matrix theory , volume 28

    L \'a szl \'o Erd o s and Horng-Tzer Yau. A dynamical approach to random matrix theory , volume 28. American Mathematical Soc., 2017

    work page 2017

  15. [17]

    Common principal components in k groups

    Bernhard N Flury. Common principal components in k groups. Journal of the American Statistical Association , 79(388):892--898, 1984

    work page 1984

  16. [18]

    A unifying tutorial on approximate message passing

    Oliver Y Feng, Ramji Venkataramanan, Cynthia Rush, and Richard J Samworth. A unifying tutorial on approximate message passing. Foundations and Trends in Machine Learning , 15(4):335--536, 2022

    work page 2022

  17. [20]

    Operator-valued semicircular elements: solving a quadratic matrix equation with positivity constraints

    J William Helton, Reza Rashidi Far, and Roland Speicher. Operator-valued semicircular elements: solving a quadratic matrix equation with positivity constraints. International Mathematics Research Notices , 2007(9):rnm086--rnm086, 2007

    work page 2007

  18. [21]

    Deterministic equivalents for certain functionals of large random matrices

    Walid Hachem, Philippe Loubaton, and Jamal Najim. Deterministic equivalents for certain functionals of large random matrices. The Annals of Applied Probability , 17(3):875--930, 2007

    work page 2007

  19. [22]

    On the distribution of the largest eigenvalue in principal components analysis

    Iain M Johnstone. On the distribution of the largest eigenvalue in principal components analysis. The Annals of statistics , 29(2):295--327, 2001

    work page 2001

  20. [23]

    Spectral redemption in clustering sparse networks

    Florent Krzakala, Cristopher Moore, Elchanan Mossel, Joe Neeman, Allan Sly, Lenka Zdeborov \'a , and Pan Zhang. Spectral redemption in clustering sparse networks. Proceedings of the National Academy of Sciences , 110(52):20935--20940, 2013

    work page 2013

  21. [24]

    The isotropic semicircle law and deformation of wigner matrices

    Antti Knowles and Jun Yin. The isotropic semicircle law and deformation of wigner matrices. Communications on Pure and Applied Mathematics , 66(11):1663--1749, 2013

    work page 2013

  22. [25]

    Optimal thresholds and algorithms for a model of multi-modal learning in high dimensions

    Christian Keup and Lenka Zdeborov \'a . Optimal thresholds and algorithms for a model of multi-modal learning in high dimensions. Journal of Statistical Mechanics: Theory and Experiment , 2025(9):093302, 2025

    work page 2025

  23. [26]

    Optimal spectral initialization for signal recovery with applications to phase retrieval

    Wangyu Luo, Wael Alghamdi, and Yue M Lu. Optimal spectral initialization for signal recovery with applications to phase retrieval. IEEE Transactions on Signal Processing , 67(9):2347--2356, 2019

    work page 2019

  24. [27]

    Computing norms of free operators with matrix coefficients

    Franz Lehner. Computing norms of free operators with matrix coefficients. American Journal of Mathematics , 121(3):453--486, 1999

    work page 1999

  25. [29]

    Phase transitions of spectral initialization for high-dimensional non-convex estimation

    Yue M Lu and Gen Li. Phase transitions of spectral initialization for high-dimensional non-convex estimation. Information and Inference: A Journal of the IMA , 9(3):507--541, 2020

    work page 2020

  26. [30]

    Fundamental limits of symmetric low-rank matrix estimation

    Marc Lelarge and L \'e o Miolane. Fundamental limits of symmetric low-rank matrix estimation. Probability Theory and Related Fields , 173:859--929, 2019

    work page 2019

  27. [31]

    Spectral phase transition and optimal pca in block-structured spiked models

    Pierre Mergny, Justin Ko, and Florent Krzakala. Spectral phase transition and optimal pca in block-structured spiked models. In Proceedings of the 41st International Conference on Machine Learning , pages 35470--35491, 2024

    work page 2024

  28. [32]

    Statistical clustering of temporal networks through a dynamic stochastic block model

    Catherine Matias and Vincent Miele. Statistical clustering of temporal networks through a dynamic stochastic block model. Journal of the Royal Statistical Society Series B: Statistical Methodology , 79(4):1119--1141, 2017

    work page 2017

  29. [33]

    Fundamental limits of weak recovery with applications to phase retrieval

    Marco Mondelli and Andrea Montanari. Fundamental limits of weak recovery with applications to phase retrieval. In Conference On Learning Theory , pages 1445--1450. PMLR, 2018

    work page 2018

  30. [34]

    A friendly tutorial on mean-field spin glass techniques for non-physicists

    Andrea Montanari and Subhabrata Sen. A friendly tutorial on mean-field spin glass techniques for non-physicists. Foundations and Trends in Machine Learning , 17(1):1--173, 2024

    work page 2024

  31. [35]

    Estimation of low-rank matrices via approximate message passing

    Andrea Montanari and Ramji Venkataramanan. Estimation of low-rank matrices via approximate message passing. The Annals of Statistics , 49(1), 2021

    work page 2021

  32. [38]

    Optimality and sub-optimality of pca i: Spiked random matrix models

    Amelia Perry, Alexander S Wein, Afonso S Bandeira, and Ankur Moitra. Optimality and sub-optimality of pca i: Spiked random matrix models. The Annals of Statistics , 46(5):2416--2451, 2018

    work page 2018

  33. [39]

    Information-theoretic limits for the matrix tensor product

    Galen Reeves. Information-theoretic limits for the matrix tensor product. IEEE Journal on Selected Areas in Information Theory , 1(3):777--798, 2020

    work page 2020

  34. [41]

    High-dimensional probability: An introduction with applications in data science , volume 47

    Roman Vershynin. High-dimensional probability: An introduction with applications in data science , volume 47. Cambridge university press, 2018

    work page 2018

  35. [42]

    High-dimensional statistics: A non-asymptotic viewpoint , volume 48

    Martin J Wainwright. High-dimensional statistics: A non-asymptotic viewpoint , volume 48. Cambridge university press, 2019

    work page 2019

  36. [43]

    Fundamental limits of community detection from multi-view data: multi-layer, dynamic and partially labeled block models

    Xiaodong Yang, Buyu Lin, and Subhabrata Sen. Fundamental limits of community detection from multi-view data: multi-layer, dynamic and partially labeled block models. The Annals of Statistics , 53(6):2728--2756, 2025

    work page 2025

  37. [44]

    Spectral estimators for structured generalized linear models via approximate message passing

    Yihan Zhang, Hong Chang Ji, Ramji Venkataramanan, and Marco Mondelli. Spectral estimators for structured generalized linear models via approximate message passing. In The Thirty Seventh Annual Conference on Learning Theory , pages 5224--5230. PMLR, 2024

    work page 2024

  38. [45]

    Matrix denoising with doubly heteroscedastic noise: Fundamental limits and optimal spectral methods

    Yihan Zhang and Marco Mondelli. Matrix denoising with doubly heteroscedastic noise: Fundamental limits and optimal spectral methods. Advances in Neural Information Processing Systems , 37:93060--93117, 2024

    work page 2024

  39. [47]

    personal communication , year=

    Optimal Spectral Algorithms for Correlated Two-view Models in High Dimensions , author=. personal communication , year=

    work page

  40. [48]

    Journal of the American Statistical Association , volume=

    Common principal components in k groups , author=. Journal of the American Statistical Association , volume=. 1984 , publisher=

    work page 1984

  41. [49]

    arXiv preprint arXiv:2211.11368 , year=

    Precise asymptotics for spectral methods in mixed generalized linear models , author=. arXiv preprint arXiv:2211.11368 , year=

    work page arXiv

  42. [50]

    IEEE Transactions on Signal Processing , volume=

    Optimal spectral initialization for signal recovery with applications to phase retrieval , author=. IEEE Transactions on Signal Processing , volume=. 2019 , publisher=

    work page 2019

  43. [51]

    Information and Inference: A Journal of the IMA , volume=

    Phase transitions of spectral initialization for high-dimensional non-convex estimation , author=. Information and Inference: A Journal of the IMA , volume=. 2020 , publisher=

    work page 2020

  44. [52]

    Conference On Learning Theory , pages=

    Fundamental limits of weak recovery with applications to phase retrieval , author=. Conference On Learning Theory , pages=. 2018 , organization=

    work page 2018

  45. [53]

    Proceedings of the National Academy of Sciences , volume=

    Spectral redemption in clustering sparse networks , author=. Proceedings of the National Academy of Sciences , volume=. 2013 , publisher=

    work page 2013

  46. [54]

    Journal of Statistical Mechanics: Theory and Experiment , volume=

    Optimal thresholds and algorithms for a model of multi-modal learning in high dimensions , author=. Journal of Statistical Mechanics: Theory and Experiment , volume=. 2025 , publisher=

    work page 2025

  47. [55]

    Preprint, arXiv:2510.17561

    Spectral thresholds in correlated spiked models and fundamental limits of partial least squares , author=. arXiv preprint arXiv:2510.17561 , year=

    work page arXiv

  48. [56]

    arXiv preprint arXiv:2407.19030 , year=

    Multimodal data integration and cross-modal querying via orchestrated approximate message passing , author=. arXiv preprint arXiv:2407.19030 , year=

    work page arXiv

  49. [57]

    arXiv preprint arXiv:2306.15580 , year=

    Approximate message passing for the matrix tensor product model , author=. arXiv preprint arXiv:2306.15580 , year=

    work page arXiv

  50. [58]

    Statistica Sinica , pages=

    Asymptotics of sample eigenstructure for a large dimensional spiked covariance model , author=. Statistica Sinica , pages=. 2007 , publisher=

    work page 2007

  51. [59]

    The Annals of statistics , volume=

    On the distribution of the largest eigenvalue in principal components analysis , author=. The Annals of statistics , volume=. 2001 , publisher=

    work page 2001

  52. [60]

    Advances in Neural Information Processing Systems , volume=

    Matrix denoising with doubly heteroscedastic noise: Fundamental limits and optimal spectral methods , author=. Advances in Neural Information Processing Systems , volume=

    work page

  53. [61]

    Two-sided bounds and applications , author=

    Matrix concentration inequalities and free probability II. Two-sided bounds and applications , author=. arXiv preprint arXiv:2406.11453 , year=

    work page arXiv

  54. [62]

    American Journal of Mathematics , volume=

    Computing norms of free operators with matrix coefficients , author=. American Journal of Mathematics , volume=. 1999 , publisher=

    work page 1999

  55. [63]

    arXiv preprint arXiv:2510.23987 , year=

    Computing extreme singular values of free operators , author=. arXiv preprint arXiv:2510.23987 , year=

    work page arXiv

  56. [64]

    Inventiones mathematicae , volume=

    Matrix concentration inequalities and free probability , author=. Inventiones mathematicae , volume=. 2023 , publisher=

    work page 2023

  57. [65]

    The Thirty Seventh Annual Conference on Learning Theory , pages=

    Spectral estimators for structured generalized linear models via approximate message passing , author=. The Thirty Seventh Annual Conference on Learning Theory , pages=. 2024 , organization=

    work page 2024

  58. [66]

    The Annals of Statistics , volume=

    Fundamental limits of community detection from multi-view data: multi-layer, dynamic and partially labeled block models , author=. The Annals of Statistics , volume=. 2025 , publisher=

    work page 2025

  59. [67]

    Physical review E , volume=

    Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications , author=. Physical review E , volume=. 2011 , publisher=

    work page 2011

  60. [68]

    arXiv preprint arXiv:2602.08173 , year=

    Fundamental Limits of Community Detection in Contextual Multi-Layer Stochastic Block Models , author=. arXiv preprint arXiv:2602.08173 , year=

    work page arXiv

  61. [69]

    Physical Review Letters , volume=

    Inference and phase transitions in the detection of modules in sparse networks , author=. Physical Review Letters , volume=. 2011 , publisher=

    work page 2011

  62. [70]

    Advances in Neural Information Processing Systems , volume=

    Contextual stochastic block models , author=. Advances in Neural Information Processing Systems , volume=

    work page

  63. [71]

    The Annals of Statistics , volume=

    Fundamental limits of detection in the spiked Wigner model , author=. The Annals of Statistics , volume=

    work page

  64. [72]

    Electron

    Contiguity and non-reconstruction results for planted partition models: the dense case , author=. Electron. J. Probab , volume=

    work page

  65. [73]

    Foundations and Trends

    A Friendly Tutorial on Mean-Field Spin Glass Techniques for Non-Physicists , author=. Foundations and Trends. 2024 , publisher=

    work page 2024

  66. [74]

    Electron

    The local semicircle law for a general class of random matrices , author=. Electron. J. Probab , volume=

    work page

  67. [75]

    2017 , publisher=

    A dynamical approach to random matrix theory , author=. 2017 , publisher=

    work page 2017

  68. [76]

    The Computer Science and Physics of Community Detection: Landscapes, Phase Transitions, and Hardness

    The computer science and physics of community detection: Landscapes, phase transitions, and hardness , author=. arXiv preprint arXiv:1702.00467 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  69. [77]

    2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS) , pages=

    Efficient bayesian estimation from few samples: community detection and related problems , author=. 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS) , pages=. 2017 , organization=

    work page 2017

  70. [78]

    Advances in Neural Information Processing Systems , volume=

    Estimating rank-one spikes from heavy-tailed noise via self-avoiding walks , author=. Advances in Neural Information Processing Systems , volume=

    work page

  71. [79]

    Proceedings of the forty-seventh annual ACM symposium on Theory of computing , pages=

    Consistency thresholds for the planted bisection model , author=. Proceedings of the forty-seventh annual ACM symposium on Theory of computing , pages=

    work page

  72. [80]

    Probability Theory and Related Fields , volume=

    Reconstruction and estimation in the planted partition model , author=. Probability Theory and Related Fields , volume=. 2015 , publisher=

    work page 2015

  73. [81]

    Information and Inference: A Journal of the IMA , volume=

    Detecting planted partition in sparse multilayer networks , author=. Information and Inference: A Journal of the IMA , volume=. 2024 , publisher=

    work page 2024

  74. [82]

    Annales de l'institut Henri Poincare , volume=

    Location of the spectrum of Kronecker random matrices , author=. Annales de l'institut Henri Poincare , volume=

    work page

  75. [83]

    Probability Theory and Related Fields , volume=

    Stability of the matrix Dyson equation and random matrices with correlations , author=. Probability Theory and Related Fields , volume=. 2019 , publisher=

    work page 2019

  76. [84]

    The matrix Dyson equation and its applications for random matrices

    The matrix Dyson equation and its applications for random matrices , author=. arXiv preprint arXiv:1903.10060 , year=

    work page internal anchor Pith review Pith/arXiv arXiv 1903

  77. [85]

    Information and Inference: A Journal of the IMA , volume=

    Asymptotic mutual information for the balanced binary stochastic block model , author=. Information and Inference: A Journal of the IMA , volume=. 2017 , publisher=

    work page 2017

  78. [86]

    The Annals of Probability , volume=

    No eigenvalues outside the support of the limiting spectral distribution of large-dimensional sample covariance matrices , author=. The Annals of Probability , volume=. 1998 , publisher=

    work page 1998

  79. [87]

    Journal of Multivariate Analysis , volume=

    Analysis of the limiting spectral distribution of large dimensional random matrices , author=. Journal of Multivariate Analysis , volume=. 1995 , publisher=

    work page 1995

  80. [88]

    The Annals of Applied Probability , volume=

    Deterministic equivalents for certain functionals of large random matrices , author=. The Annals of Applied Probability , volume=. 2007 , publisher=

    work page 2007

Showing first 80 references.