Misspecified nonconvex statistical optimization for sparse phase retrieval
From MaRDI portal
Publication:2425184
DOI10.1007/S10107-019-01364-5zbMATH Open1409.94820arXiv1712.06245OpenAlexW2962912217WikidataQ128348470 ScholiaQ128348470MaRDI QIDQ2425184FDOQ2425184
Publication date: 26 June 2019
Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)
Abstract: Existing nonconvex statistical optimization theory and methods crucially rely on the correct specification of the underlying "true" statistical models. To address this issue, we take a first step towards taming model misspecification by studying the high-dimensional sparse phase retrieval problem with misspecified link functions. In particular, we propose a simple variant of the thresholded Wirtinger flow algorithm that, given a proper initialization, linearly converges to an estimator with optimal statistical accuracy for a broad family of unknown link functions. We further provide extensive numerical experiments to support our theoretical findings.
Full work available at URL: https://arxiv.org/abs/1712.06245
Applications of mathematical programming (90C90) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Nonlinear programming (90C30)
Cites Work
- Sparse-BSOS: a bounded degree SOS hierarchy for large scale polynomial optimization with sparsity
- Phaselift: exact and stable signal recovery from magnitude measurements via convex programming
- Phase Retrieval via Wirtinger Flow: Theory and Algorithms
- Title not available (Why is that?)
- Statistics for high-dimensional data. Methods, theory and applications.
- Estimation of the mean of a multivariate normal distribution
- On consistency and sparsity for sliced inverse regression in high dimensions
- Sliced Inverse Regression for Dimension Reduction
- On Sliced Inverse Regression With High-Dimensional Covariates
- Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problems
- Title not available (Why is that?)
- On Consistency and Sparsity for Principal Components Analysis in High Dimensions
- Regression analysis under link violation
- Sparse Generalized Eigenvalue Problem: Optimal Statistical Rates via Truncated Rayleigh Flow
- Sufficient Dimension Reduction via Inverse Regression
- Semiparametric and nonparametric methods in econometrics
- On Principal Hessian Directions for Data Visualization and Dimension Reduction: Another Application of Stein's Lemma
- Optimal computational and statistical rates of convergence for sparse nonconvex learning problems
- The Generalized Lasso With Non-Linear Observations
- Proximal alternating linearized minimization for nonconvex and nonsmooth problems
- Variable selection for general index models via sliced inverse regression
- A mathematical introduction to compressive sensing
- Non-parametric analysis of a generalized regression model. The maximum rank correlation estimator
- Semidefinite programming relaxations for semialgebraic problems
- Accelerated gradient methods for nonconvex nonlinear and stochastic programming
- A Lagrangian-DNN relaxation: a fast method for computing tight lower bounds for a class of quadratic optimization problems
- Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
- Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima
- Phase recovery, MaxCut and complex semidefinite programming
- On the complexity analysis of randomized block-coordinate descent methods
- Optimal rates of convergence for noisy sparse phase retrieval via thresholded Wirtinger flow
- High dimensional single index models
- Structured Signal Recovery From Non-Linear and Heavy-Tailed Measurements
- Convergence rate bounds for a proximal ADMM with over-relaxation stepsize parameter for solving nonconvex linearly constrained problems
- Sparse single-index model
- Phase retrieval via matrix completion
- A globally convergent algorithm for nonconvex optimization based on block coordinate update
- High-dimensional estimation with geometric constraints: Table 1.
- A geometric analysis of phase retrieval
- Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems
- Phase Retrieval Using Alternating Minimization
- Phase Retrieval With Random Gaussian Sensing Vectors by Alternating Projections
- High-Dimensional Estimation of Structured Signals From Non-Linear Observations With General Convex Loss Functions
- Pathwise coordinate optimization for sparse learning: algorithm and theory
- Title not available (Why is that?)
Cited In (5)
- Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval
- Title not available (Why is that?)
- Concentration inequalities for polynomials in \(\alpha\)-sub-exponential random variables
- The sampling complexity on nonconvex sparse phase retrieval problem
- Recent Theoretical Advances in Non-Convex Optimization
Uses Software
This page was built for publication: Misspecified nonconvex statistical optimization for sparse phase retrieval
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2425184)
