Asymptotic normality and optimality in nonsmooth stochastic approximation

DOI10.1214/24-aos2401MaRDI QIDQ6621533

Liwei Jiang, Damek Shea Davis, Dmitriy Drusvyatskiy

Publication date: 18 October 2024

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

zbMATH Keywords

variational inequalityasymptotic normalitystochastic gradientlocal asymptotic minimax theoryactive manifold

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Numerical optimization and variational techniques (65K10) Stochastic programming (90C15)

Cites Work

• Unnamed Item
• Primal-dual subgradient methods for convex problems
• Optimality, identifiability, and sensitivity
• Asymptotic behavior of statistical estimators and of optimal solutions of stochastic optimization problems
• Asymptotic properties of statistical estimators in stochastic programming
• Asymptotics in statistics. Some basic concepts.
• Stochastic subgradient method converges on tame functions
• A \(\mathcal{VU}\)-algorithm for convex minimization
• Newton methods for nonsmooth convex minimization: connections among \(\mathcal U\)-Lagrangian, Riemannian Newton and SQP methods
• Asymptotic optimality in stochastic optimization
• Generic Minimizing Behavior in Semialgebraic Optimization
• Introduction to Smooth Manifolds
• Calculus Without Derivatives
• Identifiable Surfaces in Constrained Optimization
• Implicit Functions and Solution Mappings
• Acceleration of Stochastic Approximation by Averaging
• Asymptotic Statistics
• Asymptotic Theory for Solutions in Statistical Estimation and Stochastic Programming
• The 𝒰-Lagrangian of a convex function
• Active Sets, Nonsmoothness, and Sensitivity
• Prox-regular functions in variational analysis
• An Introduction to Optimization on Smooth Manifolds
• Alternating Projections on Manifolds
• On a Class of Nonsmooth Composite Functions

This page was built for publication: Asymptotic normality and optimality in nonsmooth stochastic approximation