Stochastic first-order methods for convex and nonconvex functional constrained optimization

DOI10.1007/s10107-021-01742-yOpenAlexW2976677498MaRDI QIDQ2689819

Digvijay Boob, Qi Deng, Guanghui Lan

Publication date: 14 March 2023

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1908.02734

zbMATH Keywords

accelerationstochastic algorithmsfunctional constrained optimizationconvex and nonconvex optimization

Mathematics Subject Classification ID

Semidefinite programming (90C22) Convex programming (90C25) Large-scale problems in mathematical programming (90C06) Numerical methods based on nonlinear programming (49M37)

Related Items (5)

First-Order Methods for Problems with $O$(1) Functional Constraints Can Have Almost the Same Convergence Rate as for Unconstrained Problems ⋮ An accelerated inexact dampened augmented Lagrangian method for linearly-constrained nonconvex composite optimization problems ⋮ Stochastic inexact augmented Lagrangian method for nonconvex expectation constrained optimization ⋮ Unnamed Item ⋮ Provably training overparameterized neural network classifiers with non-convex constraints

Uses Software

• ProxSARAH

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Accelerated gradient methods for nonconvex nonlinear and stochastic programming
• Lectures on convex optimization
• A practical optimality condition without constraint qualifications for nonlinear programming
• Level-set methods for convex optimization
• Non-Euclidean restricted memory level method for large-scale convex optimization
• An optimal randomized incremental gradient method
• New variants of bundle methods
• A first-order primal-dual algorithm for convex problems with applications to imaging
• Iteration-complexity of first-order penalty methods for convex programming
• Communication-efficient algorithms for decentralized and stochastic optimization
• First-order and stochastic optimization methods for machine learning
• On the complexity of finding first-order critical points in constrained nonlinear optimization
• The Fritz John necessary optimality conditions in the presence of equality and inequality constraints
• Penalty methods with stochastic approximation for stochastic nonlinear programming
• New Proximal Point Algorithms for Convex Minimization
• A Level-Set Method for Convex Optimization with a Feasible Solution Path
• Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
• Strict Constraint Qualifications and Sequential Optimality Conditions for Constrained Optimization
• Optimal Primal-Dual Methods for a Class of Saddle Point Problems
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• On sequential optimality conditions for smooth constrained optimization
• Iteration-complexity of first-order augmented Lagrangian methods for convex programming

This page was built for publication: Stochastic first-order methods for convex and nonconvex functional constrained optimization