Entrywise dynamics and universality of general first order methods (Q6926362)

!

This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:

Entrywise dynamics and universality of general first order methods

scientific article; zbMATH DE number 8097077

Language	Label	Description	Also known as
default for all languages	No label defined
English	Entrywise dynamics and universality of general first order methods	scientific article; zbMATH DE number 8097077

Statements

instance of

scholarly article

0 references

title

Entrywise dynamics and universality of general first order methods (English)

0 references

author

Qiyang Han

0 references

published in

The Annals of Statistics

0 references

publication date

24 September 2025

0 references

full work available at URL

https://projecteuclid.org/journals/annals-of-statistics/volume-53/issue-4/Entrywise-dynamics-and-universality-of-general-first-order-methods/10.1214/25-AOS2544.full

0 references

zbMATH Keywords

general first order methods

0 references

approximate message passing

0 references

random matrix theory

0 references

delocalization

0 references

empirical risk minimization

0 references

gradient descent

0 references

logistic regression

0 references

Gaussian approximations

0 references

MaRDI profile type

MaRDI publication profile

0 references

cites work

Local law of addition of random matrices on optimal scale

0 references

A leave-one-out approach to approximate message passing

0 references

Universality in polytope phase transitions and message passing algorithms

0 references

The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing

0 references

The LASSO Risk for Gaussian Matrices

0 references

Debiasing convex regularized estimators and interval estimation in linear models

0 references

State evolution for approximate message passing with non-separable functions

0 references

Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing

0 references

A non-asymptotic analysis of generalized vector approximate message passing algorithms with rotationally invariant designs

0 references

The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression

0 references

The Lasso with general Gaussian designs with applications to hypothesis testing

0 references

A generalization of the Lindeberg principle

0 references

Universality of approximate message passing algorithms

0 references

On convergence of the cavity and Bolthausen's TAP iterations to the local magnetization

0 references

High dimensional robust M-estimation: asymptotic variance via approximate message passing

0 references

Universality of approximate message passing with semirandom matrices

0 references

Spectral universality in regularized linear regression with nearly deterministic sensing matrices

0 references

On the impact of predictor geometry on the performance on high-dimensional ridge-regularized generalized robust regression estimators

0 references

Approximate message passing algorithms for rotationally invariant matrices

0 references

Asymptotic Errors for Teacher-Student Convex Generalized Linear Models (Or: How to Prove Kabashima’s Replica Formula)

0 references

Rigorous dynamical mean field theory for stochastic gradient descent methods

0 references

Some inequalities for Gaussian processes and applications

0 references

Stein's method for the TAP equations an iterative scheme for the SK model

0 references

Approximate message passing for sparse matrices with application to the equilibria of large ecological Lotka-Volterra systems

0 references

Noisy linear inverse problems under convex constraints: exact risk asymptotics in high dimensions

0 references

Universality of regularized regression estimators in high dimensions

0 references

Entrywise dynamics and universality of general first order methods

0 references

Surprises in high-dimensional ridgeless least squares interpolation

0 references

Universality Laws for High-Dimensional Learning With Random Features

0 references

A new central limit theorem for the augmented IPW estimator: variance inflation, cross-fit covariance and beyond

0 references

The isotropic semicircle law and deformation of Wigner matrices

0 references

Anisotropic local laws for random matrices

0 references

Applications of the Lindeberg Principle in Communications and Statistical Learning

0 references

The distribution of the Lasso: uniform control over sparse balls and adaptive parameter tuning

0 references

The generalization error of max-margin linear classifiers: benign overfitting and high dimensional asymptotics in the overparametrized regime

0 references

Statistically optimal firstorder algorithms: a proof via orthogonalization

0 references

Universality laws for randomized dimension reduction, with applications

0 references

Finite Sample Analysis of Approximate Message Passing Algorithms

0 references

A modern maximum-likelihood theory for high-dimensional logistic regression

0 references

The likelihood ratio test in high-dimensional logistic regression is asymptotically a rescaled Chi-square

0 references

Precise Error Analysis of Regularized <inline-formula> <tex-math notation="LaTeX">$M$ </tex-math> </inline-formula>-Estimators in High Dimensions

0 references

Asymptotic Statistics

0 references

Universality of approximate message passing algorithms and tensor networks

0 references

The asymptotic distribution of the MLE in high-dimensional logistic models: arbitrary covariance

0 references

Identifiers

zbMATH Open document ID

1572.60007

0 references

DOI

10.1214/25-AOS2544

0 references

Mathematics Subject Classification ID

0 references

0 references

0 references

0 references

Sitelinks

Mathematics(1 entry)

mardi Entrywise dynamics and universality of general first order methods