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

DOI10.1214/23-aos2301arXiv2201.08435OpenAlexW4387819051MaRDI QIDQ6183752

Qiyang Han

Publication date: 4 January 2024

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.08435

zbMATH Keywords

fixed-point equationlinear inverse problemGaussian sequence modelhigh-dimensional asymptotics

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Nonparametric hypothesis testing (62G10) Central limit and other weak theorems (60F05) Approximations to statistical distributions (nonasymptotic) (62E17)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Sharp MSE bounds for proximal denoising
• High dimensional robust M-estimation: asymptotic variance via approximate message passing
• A new perspective on least squares under convex constraint
• Gaussian phase transitions and conic intrinsic volumes: steining the Steiner formula
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• On the impact of predictor geometry on the performance on high-dimensional ridge-regularized generalized robust regression estimators
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• On the degrees of freedom in shrinkage estimation
• Some inequalities for Gaussian processes and applications
• Exponential integrability and transportation cost related to logarithmic Sobolev inequalities
• On concentration for (regularized) empirical risk minimization
• Nonparametric shape-restricted regression
• Fundamental limits of symmetric low-rank matrix estimation
• Sharp oracle inequalities for least squares estimators in shape restricted regression
• Weak convergence and empirical processes. With applications to statistics
• The convex geometry of linear inverse problems
• Bayesian and frequentist regression methods
• Limit distribution theory for block estimators in multiple isotonic regression
• Multivariate extensions of isotonic regression and total variation denoising via entire monotonicity and Hardy-Krause variation
• The distribution of the Lasso: uniform control over sparse balls and adaptive parameter tuning
• Fundamental barriers to high-dimensional regression with convex penalties
• High-dimensional asymptotics of likelihood ratio tests in the Gaussian sequence model under convex constraints
• Berry-Esseen bounds for Chernoff-type nonstandard asymptotics in isotonic regression
• A precise high-dimensional asymptotic theory for boosting and minimum-\(\ell_1\)-norm interpolated classifiers
• From Gauss to Kolmogorov: localized measures of complexity for ellipses
• Isotonic regression in general dimensions
• On matrix estimation under monotonicity constraints
• On risk bounds in isotonic and other shape restricted regression problems
• Convex Recovery of a Structured Signal from Independent Random Linear Measurements
• Nonparametric Estimation under Shape Constraints
• On robust regression with high-dimensional predictors
• From Denoising to Compressed Sensing
• Mathematical Foundations of Infinite-Dimensional Statistical Models
• Recovering Structured Signals in Noise: Least-Squares Meets Compressed Sensing
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
• Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
• Nonnegative Matrix Factorization Based on Alternating Nonnegativity Constrained Least Squares and Active Set Method
• Hypothesis tests for normal means constrained by linear inequalities
• Precise Error Analysis of Regularized <inline-formula> <tex-math notation="LaTeX">$M$ </tex-math> </inline-formula>-Estimators in High Dimensions
• State evolution for approximate message passing with non-separable functions
• MEAN FIELD ASYMPTOTICS IN HIGH-DIMENSIONAL STATISTICS: FROM EXACT RESULTS TO EFFICIENT ALGORITHMS
• State evolution for general approximate message passing algorithms, with applications to spatial coupling
• Living on the edge: phase transitions in convex programs with random data
• A modern maximum-likelihood theory for high-dimensional logistic regression
• Optimal errors and phase transitions in high-dimensional generalized linear models
• Universality laws for randomized dimension reduction, with applications
• The LASSO Risk for Gaussian Matrices
• The Noise-Sensitivity Phase Transition in Compressed Sensing
• The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
• Sharp Time–Data Tradeoffs for Linear Inverse Problems
• Stable signal recovery from incomplete and inaccurate measurements
• A multivariate analogue of the one-sided test
• Compressed sensing
• Sharp global convergence guarantees for iterative nonconvex optimization with random data
• Debiasing convex regularized estimators and interval estimation in linear models