Precise asymptotics for spectral methods in mixed generalized linear models

DOI10.1137/24M1702854MaRDI QIDQ7300555zbMATH OpenFDO

Authors Yihan Zhang, Marco Mondelli, Ramji Venkataramanan

Publication date 21 July 2026

Published in SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1137/24M1702854

Mathematics Subject Classification ID

Estimation in multivariate analysis (62H12) Linear regression; mixed models (62J05) Generalized linear models (logistic models) (62J12)

Cites work

• \(\ell_{1}\)-penalization for mixture regression models
• A modern maximum-likelihood theory for high-dimensional logistic regression
• A theory of solving TAP equations for Ising models with general invariant random matrices
• A Unifying Tutorial on Approximate Message Passing
• Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing
• Analysis of Spectral Methods for Phase Retrieval With Random Orthogonal Matrices
• Approximate message passing algorithms for rotationally invariant matrices
• Approximate message passing for orthogonally invariant ensembles: multivariate non-linearities and spectral initialization
• Asymptotically liberating sequences of random unitary matrices
• Bayesian Inference in Mixtures-of-Experts and Hierarchical Mixtures-of-Experts Models With an Application to Speech Recognition
• Bulk universality for generalized Wigner matrices
• Capacity of Channels With Frequency-Selective and Time-Selective Fading
• Clustering electricity consumers using high-dimensional regression mixture models
• Compressive Phase Retrieval via Generalized Approximate Message Passing
• Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications
• Estimating the Coefficients of a Mixture of Two Linear Regressions by Expectation Maximization
• Estimation of low-rank matrices via approximate message passing
• Finite Sample Analysis of Approximate Message Passing Algorithms
• Fitting mixtures of linear regressions
• Fundamental limits of weak recovery with applications to phase retrieval
• High dimensional robust M-estimation: asymptotic variance via approximate message passing
• High-dimensional estimation with geometric constraints
• scientific article; zbMATH DE number 47310 (Why is no real title available?)
• Learning mixtures of linear regressions in subexponential time via Fourier moments
• Limiting empirical singular value distribution of restrictions of discrete Fourier transform matrices
• On Principal Hessian Directions for Data Visualization and Dimension Reduction: Another Application of Stein's Lemma
• Optimal combination of linear and spectral estimators for generalized linear models
• Optimal errors and phase transitions in high-dimensional generalized linear models
• Optimal Spectral Initialization for Signal Recovery With Applications to Phase Retrieval
• Outliers in the spectrum of large deformed unitarily invariant models
• Phase transitions of spectral initialization for high-dimensional non-convex estimation
• Phaselift: exact and stable signal recovery from magnitude measurements via convex programming
• Random matrices: localization of the eigenvalues and the necessity of four moments
• Rigorous Dynamics of Expectation-Propagation-Based Signal Recovery from Unitarily Invariant Measurements
• Sharp global convergence guarantees for iterative nonconvex optimization with random data
• Spectral universality in regularized linear regression with nearly deterministic sensing matrices
• State evolution for general approximate message passing algorithms, with applications to spatial coupling
• Statistical guarantees for the EM algorithm: from population to sample-based analysis
• The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
• The LASSO Risk for Gaussian Matrices
• The numerics of phase retrieval
• Universality in polytope phase transitions and message passing algorithms
• Universality of approximate message passing algorithms
• Universality of approximate message passing algorithms and tensor networks
• Universality of approximate message passing with semirandom matrices
• Universality of Linearized Message Passing for Phase Retrieval With Structured Sensing Matrices
• Variable Selection in Finite Mixture of Regression Models
• Vector Approximate Message Passing

This page was built for publication: Precise asymptotics for spectral methods in mixed generalized linear models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7300555)