Optimal combination of linear and spectral estimators for generalized linear models
DOI10.1007/s10208-021-09531-xOpenAlexW3195065261MaRDI QIDQ2088138
Marco Mondelli, Ramji Venkataramanan, Christos Thrampoulidis
Publication date: 21 October 2022
Published in: Foundations of Computational Mathematics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2008.03326
generalized linear modelsapproximate message passinglinear estimatorspectral estimatorBayes optimalityweak recovery
Computational learning theory (68Q32) Generalized linear models (logistic models) (62J12) Learning and adaptive systems in artificial intelligence (68T05) Statistical aspects of information-theoretic topics (62B10)
Uses Software
Cites Work
- Approximation by log-concave distributions, with applications to regression
- Regression analysis under link violation
- Fundamental limits of weak recovery with applications to phase retrieval
- Phase recovery, MaxCut and complex semidefinite programming
- Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
- Estimation of low-rank matrices via approximate message passing
- L1-Regularized Least Squares for Support Recovery of High Dimensional Single Index Models with Gaussian Designs
- PhaseLift: Exact and Stable Signal Recovery from Magnitude Measurements via Convex Programming
- The Generalized Lasso With Non-Linear Observations
- Phase Retrieval via Wirtinger Flow: Theory and Algorithms
- Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications
- Solving systems of phaseless equations via Kaczmarz methods: a proof of concept study
- Maximum likelihood estimation of liner signal parameters for Poisson processes
- On Principal Hessian Directions for Data Visualization and Dimension Reduction: Another Application of Stein's Lemma
- Recursive consistent estimation with bounded noise
- Finite Sample Analysis of Approximate Message Passing Algorithms
- PhaseMax: Convex Phase Retrieval via Basis Pursuit
- Compressive Phase Retrieval via Generalized Approximate Message Passing
- High-dimensional estimation with geometric constraints: Table 1.
- High-Dimensional Probability
- Structured Signal Recovery From Non-Linear and Heavy-Tailed Measurements
- State evolution for approximate message passing with non-separable functions
- Analysis of Spectral Methods for Phase Retrieval With Random Orthogonal Matrices
- State evolution for general approximate message passing algorithms, with applications to spatial coupling
- Recovering Structured Data From Superimposed Non-Linear Measurements
- A modern maximum-likelihood theory for high-dimensional logistic regression
- Optimal errors and phase transitions in high-dimensional generalized linear models
- Optimal Spectral Initialization for Signal Recovery With Applications to Phase Retrieval
- The LASSO Risk for Gaussian Matrices
- High-Dimensional Estimation of Structured Signals From Non-Linear Observations With General Convex Loss Functions
- The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
- Bits From Photons: Oversampled Image Acquisition Using Binary Poisson Statistics
- Phase Retrieval via Matrix Completion
This page was built for publication: Optimal combination of linear and spectral estimators for generalized linear models
