Asymptotic Properties of Stationary Solutions of Coupled Nonconvex Nonsmooth Empirical Risk Minimization

DOI10.1287/moor.2021.1198OpenAlexW3212315643MaRDI QIDQ5868947

Yu Feng Liu, Ying Cui, Jong-Shi Pang, Zhengling Qi

Publication date: 26 September 2022

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1910.02488

zbMATH Keywords

convergence ratesasymptotic distributionconsistencystatistical analysisnonconvexitynonsmoothnessdirectional stationarityphase-retrieval problem

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Nonconvex programming, global optimization (90C26) Nonsmooth analysis (49J52)

Uses Software

• Wirtinger Flow

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Statistical inference for the mean outcome under a possibly non-unique optimal treatment strategy
• High-dimensional regression with noisy and missing data: provable guarantees with nonconvexity
• Uniform laws of large numbers for set-valued mappings and subdifferentials of random functions
• Smooth sample average approximation of stationary points in nonsmooth stochastic optimization and applications
• Asymptotic behavior of statistical estimators and of optimal solutions of stochastic optimization problems
• Asymptotic properties of statistical estimators in stochastic programming
• Sample-path solution of stochastic variational inequalities
• The DC (Difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems
• A geometric analysis of phase retrieval
• On the asymptotics of constrained \(M\)-estimation
• Weak convergence and empirical processes. With applications to statistics
• The landscape of empirical risk for nonconvex losses
• Statistical consistency and asymptotic normality for high-dimensional robust \(M\)-estimators
• A study of piecewise linear-quadratic programs
• Approximations of semicontinuous functions with applications to stochastic optimization and statistical estimation
• Variational analysis of constrained M-estimators
• Stochastic subgradient method converges on tame functions
• Statistical estimation of composite risk functionals and risk optimization problems
• Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval
• Enhanced proximal DC algorithms with extrapolation for a class of structured nonsmooth DC minimization
• Computing B-Stationary Points of Nonsmooth DC Programs
• Phase Retrieval via Wirtinger Flow: Theory and Algorithms
• SAMPLE AVERAGE APPROXIMATION METHODS FOR A CLASS OF STOCHASTIC VARIATIONAL INEQUALITY PROBLEMS
• Lectures on Stochastic Programming
• Robust Stochastic Approximation Approach to Stochastic Programming
• Acceleration of Stochastic Approximation by Averaging
• Variational Analysis
• Asymptotic Statistics
• Composite Difference-Max Programs for Modern Statistical Estimation Problems
• Solving Systems of Random Quadratic Equations via Truncated Amplitude Flow
• Asymptotic Theory for Solutions in Statistical Estimation and Stochastic Programming
• Finite-Dimensional Variational Inequalities and Complementarity Problems
• Solving (most) of a set of quadratic equalities: composite optimization for robust phase retrieval
• Optimization-Based AMP for Phase Retrieval: The Impact of Initialization and $\ell_{2}$ Regularization
• Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima
• On the Assumptions Used to Prove Asymptotic Normality of Maximum Likelihood Estimates
• Note on the Consistency of the Maximum Likelihood Estimate
• A Stochastic Approximation Method
• On the Distribution of the Likelihood Ratio
• On a Stochastic Approximation Method
• The nonsmooth landscape of phase retrieval